ICLR 2022 Papers

Skip to yearly menu bar Skip to main content

Browse

mini compact topic detail

Distributionally Robust Fair Principal Components via Geodesic Descents

Ancestral protein sequence reconstruction using a tree-structured Ornstein-Uhlenbeck variational autoencoder

The Efficiency Misnomer

The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks

Huber Additive Models for Non-stationary Time Series Analysis

Rethinking Supervised Pre-Training for Better Downstream Transferring

Optimization inspired Multi-Branch Equilibrium Models

Know Your Action Set: Learning Action Relations for Reinforcement Learning

On the Importance of Difficulty Calibration in Membership Inference Attacks

Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset

Rethinking Class-Prior Estimation for Positive-Unlabeled Learning

Enabling Arbitrary Translation Objectives with Adaptive Tree Search

Fine-grained Differentiable Physics: A Yarn-level Model for Fabrics

Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models

SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation

Is Importance Weighting Incompatible with Interpolating Classifiers?

DIVA: Dataset Derivative of a Learning Task

Path Integral Sampler: A Stochastic Control Approach For Sampling

Feature Kernel Distillation

Representation Learning for Online and Offline RL in Low-rank MDPs

Tackling the Generative Learning Trilemma with Denoising Diffusion GANs

Strength of Minibatch Noise in SGD

Sample Selection with Uncertainty of Losses for Learning with Noisy Labels

Online Facility Location with Predictions

High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize

Contrastive Fine-grained Class Clustering via Generative Adversarial Networks

TAMP-S2GCNets: Coupling Time-Aware Multipersistence Knowledge Representation with Spatio-Supra Graph Convolutional Networks for Time-Series Forecasting

D-CODE: Discovering Closed-form ODEs from Observed Trajectories

Declarative nets that are equilibrium models

Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural Networks

DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

Graph-Relational Domain Adaptation

On the approximation properties of recurrent encoder-decoder architectures

Learning Object-Oriented Dynamics for Planning from Text

Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation

The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions

AlphaZero-based Proof Cost Network to Aid Game Solving

Open-World Semi-Supervised Learning

A generalization of the randomized singular value decomposition

Learning Graphon Mean Field Games and Approximate Nash Equilibria

A Neural Tangent Kernel Perspective of Infinite Tree Ensembles

Multitask Prompted Training Enables Zero-Shot Task Generalization

On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning

On the benefits of maximum likelihood estimation for Regression and Forecasting

Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods

Universalizing Weak Supervision

Uncertainty Modeling for Out-of-Distribution Generalization

Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness

Neural Link Prediction with Walk Pooling

On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning

When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?

Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models

Crystal Diffusion Variational Autoencoder for Periodic Material Generation

High Probability Generalization Bounds with Fast Rates for Minimax Problems

Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking

Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations

Multimeasurement Generative Models

Generalized Natural Gradient Flows in Hidden Convex-Concave Games and GANs

Solving Inverse Problems in Medical Imaging with Score-Based Generative Models

switch-GLAT: Multilingual Parallel Machine Translation Via Code-Switch Decoder

MAML is a Noisy Contrastive Learner in Classification

A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion

Implicit Bias of Adversarial Training for Deep Neural Networks

Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration

POETREE: Interpretable Policy Learning with Adaptive Decision Trees

A Johnson-Lindenstrauss Framework for Randomly Initialized CNNs

Online Ad Hoc Teamwork under Partial Observability

Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games

Neural Networks as Kernel Learners: The Silent Alignment Effect

A Fine-Grained Analysis on Distribution Shift

The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Design

Towards Evaluating the Robustness of Neural Networks Learned by Transduction

GradSign: Model Performance Inference with Theoretical Insights

Consistent Counterfactuals for Deep Models

The Three Stages of Learning Dynamics in High-dimensional Kernel Methods

Real-Time Neural Voice Camouflage

Sample Efficient Stochastic Policy Extragradient Algorithm for Zero-Sum Markov Game

Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100

The Effects of Invertibility on the Representational Complexity of Encoders in Variational Autoencoders

Extending the WILDS Benchmark for Unsupervised Adaptation

Efficiently Modeling Long Sequences with Structured State Spaces

Unified Visual Transformer Compression

NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy

Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting

A Theory of Tournament Representations

Mapping conditional distributions for domain adaptation under generalized target shift

NeuPL: Neural Population Learning

An Operator Theoretic View On Pruning Deep Neural Networks

MetaMorph: Learning Universal Controllers with Transformers

PER-ETD: A Polynomially Efficient Emphatic Temporal Difference Learning Method

Modular Lifelong Reinforcement Learning via Neural Composition

TPU-GAN: Learning temporal coherence from dynamic point cloud sequences

Learning Hierarchical Structures with Differentiable Nondeterministic Stacks

Missingness Bias in Model Debugging

Accelerated Policy Learning with Parallel Differentiable Simulation

Causal Contextual Bandits with Targeted Interventions

Learning Altruistic Behaviours in Reinforcement Learning without External Rewards

FILIP: Fine-grained Interactive Language-Image Pre-Training

Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation

The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program

Variational oracle guiding for reinforcement learning

P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse Prompts

Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization

Cross-Lingual Transfer with Class-Weighted Language-Invariant Representations

Reverse Engineering of Imperceptible Adversarial Image Perturbations

Pareto Policy Adaptation

Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias

Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Design

C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks

Understanding Domain Randomization for Sim-to-real Transfer

Model-Based Offline Meta-Reinforcement Learning with Regularization

Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimation

Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface

TRGP: Trust Region Gradient Projection for Continual Learning

Contextualized Scene Imagination for Generative Commonsense Reasoning

Shallow and Deep Networks are Near-Optimal Approximators of Korobov Functions

Phenomenology of Double Descent in Finite-Width Neural Networks

InfinityGAN: Towards Infinite-Pixel Image Synthesis

Discovering Nonlinear PDEs from Scarce Data with Physics-encoded Learning

COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks

How Much Can CLIP Benefit Vision-and-Language Tasks?

Learning Causal Models from Conditional Moment Restrictions by Importance Weighting

Learning Optimal Conformal Classifiers

Self-Supervision Enhanced Feature Selection with Correlated Gates

Understanding the Variance Collapse of SVGD in High Dimensions

Information Bottleneck: Exact Analysis of (Quantized) Neural Networks

CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting

OBJECT DYNAMICS DISTILLATION FOR SCENE DECOMPOSITION AND REPRESENTATION

$\beta$-Intact-VAE: Identifying and Estimating Causal Effects under Limited Overlap

Augmented Sliced Wasserstein Distances

Neural Processes with Stochastic Attention: Paying more attention to the context dataset

Learnability of convolutional neural networks for infinite dimensional input via mixed and anisotropic smoothness

Towards General Function Approximation in Zero-Sum Markov Games

Energy-Based Learning for Cooperative Games, with Applications to Valuation Problems in Machine Learning

Counterfactual Plans under Distributional Ambiguity

Boosted Curriculum Reinforcement Learning

TAda! Temporally-Adaptive Convolutions for Video Understanding

Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations

$\mathrm{SO}(2)$-Equivariant Reinforcement Learning

Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference

Bayesian Modeling and Uncertainty Quantification for Learning to Optimize: What, Why, and How

Equivariant Graph Mechanics Networks with Constraints

THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling

SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training

Understanding Dimensional Collapse in Contrastive Self-supervised Learning

Constrained Physical-Statistics Models for Dynamical System Identification and Prediction

Anti-Concentrated Confidence Bonuses For Scalable Exploration

Learning Distributionally Robust Models at Scale via Composite Optimization

On Predicting Generalization using GANs

Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization

Deep Point Cloud Reconstruction

Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series

Half-Inverse Gradients for Physical Deep Learning

Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?

On the relation between statistical learning and perceptual distances

Graph-based Nearest Neighbor Search in Hyperbolic Spaces

Generalized rectifier wavelet covariance models for texture synthesis

Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations

PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series

Variational Neural Cellular Automata

On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks

Generalization Through the Lens of Leave-One-Out Error

Variational methods for simulation-based inference

Diurnal or Nocturnal? Federated Learning of Multi-branch Networks from Periodically Shifting Distributions

Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning

Practical Conditional Neural Process Via Tractable Dependent Predictions

CodeTrek: Flexible Modeling of Code using an Extensible Relational Representation

Selective Ensembles for Consistent Predictions

Multi-Stage Episodic Control for Strategic Exploration in Text Games

Surreal-GAN:Semi-Supervised Representation Learning via GAN for uncovering heterogeneous disease-related imaging patterns

A First-Occupancy Representation for Reinforcement Learning

Space-Time Graph Neural Networks

Offline Reinforcement Learning with Value-based Episodic Memory

The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models

Defending Against Image Corruptions Through Adversarial Augmentations

Object Pursuit: Building a Space of Objects via Discriminative Weight Generation

The Spectral Bias of Polynomial Neural Networks

Synchromesh: Reliable Code Generation from Pre-trained Language Models

Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction

Fast topological clustering with Wasserstein distance

Skill-based Meta-Reinforcement Learning

Differentiable Scaffolding Tree for Molecule Optimization

Revisiting Design Choices in Offline Model Based Reinforcement Learning

An Experimental Design Perspective on Model-Based Reinforcement Learning

The Evolution of Uncertainty of Learning in Games

CoMPS: Continual Meta Policy Search

Reinforcement Learning in Presence of Discrete Markovian Context Evolution

Provable Learning-based Algorithm For Sparse Recovery

Granger causal inference on DAGs identifies genomic loci regulating transcription

Curriculum learning as a tool to uncover learning principles in the brain

Learning Temporally Causal Latent Processes from General Temporal Data

Autoregressive Quantile Flows for Predictive Uncertainty Estimation

Bi-linear Value Networks for Multi-goal Reinforcement Learning

Deep ReLU Networks Preserve Expected Length

Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap

HyperDQN: A Randomized Exploration Method for Deep Reinforcement Learning

What Do We Mean by Generalization in Federated Learning?

A Comparison of Hamming Errors of Representative Variable Selection Methods

Model Zoo: A Growing Brain That Learns Continually

Distributional Reinforcement Learning with Monotonic Splines

Anisotropic Random Feature Regression in High Dimensions

Modeling Label Space Interactions in Multi-label Classification using Box Embeddings

Variational Predictive Routing with Nested Subjective Timescales

Training invariances and the low-rank phenomenon: beyond linear networks

A NON-PARAMETRIC REGRESSION VIEWPOINT : GENERALIZATION OF OVERPARAMETRIZED DEEP RELU NETWORK UNDER NOISY OBSERVATIONS

Top-N: Equivariant Set and Graph Generation without Exchangeability

LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5

How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning

FedChain: Chained Algorithms for Near-optimal Communication Cost in Federated Learning

Eigencurve: Optimal Learning Rate Schedule for SGD on Quadratic Objectives with Skewed Hessian Spectrums

Reinforcement Learning under a Multi-agent Predictive State Representation Model: Method and Theory

Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop

Representational Continuity for Unsupervised Continual Learning

Context-Aware Sparse Deep Coordination Graphs

The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models

Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models

Towards Understanding Generalization via Decomposing Excess Risk Dynamics

Chunked Autoregressive GAN for Conditional Waveform Synthesis

Topological Experience Replay

Generalisation in Lifelong Reinforcement Learning through Logical Composition

Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System

Discovering Invariant Rationales for Graph Neural Networks

DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools

Encoding Weights of Irregular Sparsity for Fixed-to-Fixed Model Compression

Normalization of Language Embeddings for Cross-Lingual Alignment

Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimality

Do We Need Anisotropic Graph Neural Networks?

Learning to Guide and to be Guided in the Architect-Builder Problem

Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems

Towards a Unified View of Parameter-Efficient Transfer Learning

Few-Shot Backdoor Attacks on Visual Object Tracking

Relational Learning with Variational Bayes

Scattering Networks on the Sphere for Scalable and Rotationally Equivariant Spherical CNNs

GATSBI: Generative Adversarial Training for Simulation-Based Inference

Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation

Increasing the Cost of Model Extraction with Calibrated Proof of Work

BAM: Bayes with Adaptive Memory

Open-Set Recognition: A Good Closed-Set Classifier is All You Need

Is High Variance Unavoidable in RL? A Case Study in Continuous Control

Predicting Physics in Mesh-reduced Space with Temporal Attention

Constructing a Good Behavior Basis for Transfer using Generalized Policy Updates

Lipschitz-constrained Unsupervised Skill Discovery

Task Relatedness-Based Generalization Bounds for Meta Learning

Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration

Universal Approximation Under Constraints is Possible with Transformers

Unraveling Model-Agnostic Meta-Learning via The Adaptation Learning Rate

LORD: Lower-Dimensional Embedding of Log-Signature in Neural Rough Differential Equations

Improving Federated Learning Face Recognition via Privacy-Agnostic Clusters

On the Learning and Learnability of Quasimetrics

Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization

Disentanglement Analysis with Partial Information Decomposition

Emergent Communication at Scale

Associated Learning: an Alternative to End-to-End Backpropagation that Works on CNN, RNN, and Transformer

Optimal Transport for Long-Tailed Recognition with Learnable Cost Matrix

Adversarially Robust Conformal Prediction

Generative Pseudo-Inverse Memory

Improving the Accuracy of Learning Example Weights for Imbalance Classification

Learning meta-features for AutoML

Denoising Likelihood Score Matching for Conditional Score-based Data Generation

Meta Discovery: Learning to Discover Novel Classes given Very Limited Data

Neural Markov Controlled SDE: Stochastic Optimization for Continuous-Time Data

A New Perspective on "How Graph Neural Networks Go Beyond Weisfeiler-Lehman?"

Representation-Agnostic Shape Fields

MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts

Looking Back on Learned Experiences For Class/task Incremental Learning

Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable

Acceleration of Federated Learning with Alleviated Forgetting in Local Training

Delaunay Component Analysis for Evaluation of Data Representations

Equivariant Transformers for Neural Network based Molecular Potentials

Long Expressive Memory for Sequence Modeling

Training Transition Policies via Distribution Matching for Complex Tasks

Spherical Message Passing for 3D Molecular Graphs

Wisdom of Committees: An Overlooked Approach To Faster and More Accurate Models

Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise

Large-Scale Representation Learning on Graphs via Bootstrapping

VAE Approximation Error: ELBO and Exponential Families

Label Leakage and Protection in Two-party Split Learning

Online Adversarial Attacks

Discrepancy-Based Active Learning for Domain Adaptation

Bootstrapping Semantic Segmentation with Regional Contrast

Gradient Matching for Domain Generalization

Open-vocabulary Object Detection via Vision and Language Knowledge Distillation

DISSECT: Disentangled Simultaneous Explanations via Concept Traversals

Exploring Memorization in Adversarial Training

When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations

NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning

Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL

Incremental False Negative Detection for Contrastive Learning

Learning Curves for SGD on Structured Features

AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation

Generative Models as a Data Source for Multiview Representation Learning

Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields

Reliable Adversarial Distillation with Unreliable Teachers

Automated Self-Supervised Learning for Graphs

Stein Latent Optimization for Generative Adversarial Networks

Is Homophily a Necessity for Graph Neural Networks?

Boosting Randomized Smoothing with Variance Reduced Classifiers

Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs

Query Embedding on Hyper-Relational Knowledge Graphs

Steerable Partial Differential Operators for Equivariant Neural Networks

Learning Multimodal VAEs through Mutual Supervision

Charformer: Fast Character Transformers via Gradient-based Subword Tokenization

Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity

The MultiBERTs: BERT Reproductions for Robustness Analysis

ViTGAN: Training GANs with Vision Transformers

Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions

TAPEX: Table Pre-training via Learning a Neural SQL Executor

Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning

CycleMLP: A MLP-like Architecture for Dense Prediction

Heteroscedastic Temporal Variational Autoencoder For Irregularly Sampled Time Series

Perceiver IO: A General Architecture for Structured Inputs & Outputs

SphereFace2: Binary Classification is All You Need for Deep Face Recognition

Policy Gradients Incorporating the Future

SimVLM: Simple Visual Language Model Pretraining with Weak Supervision

Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners

NASI: Label- and Data-agnostic Neural Architecture Search at Initialization

How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data

Divisive Feature Normalization Improves Image Recognition Performance in AlexNet

Finetuned Language Models are Zero-Shot Learners

CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation

Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative

Hindsight Foresight Relabeling for Meta-Reinforcement Learning

Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning

Learning to Downsample for Segmentation of Ultra-High Resolution Images

Vitruvion: A Generative Model of Parametric CAD Sketches

IGLU: Efficient GCN Training via Lazy Updates

Random matrices in service of ML footprint: ternary random features with no performance loss

Geometric and Physical Quantities improve E(3) Equivariant Message Passing

PoNet: Pooling Network for Efficient Token Mixing in Long Sequences

Focus on the Common Good: Group Distributional Robustness Follows

Task Affinity with Maximum Bipartite Matching in Few-Shot Learning

8-bit Optimizers via Block-wise Quantization

Graphon based Clustering and Testing of Networks: Algorithms and Theory

The Information Geometry of Unsupervised Reinforcement Learning

VC dimension of partially quantized neural networks in the overparametrized regime

EntQA: Entity Linking as Question Answering

Evaluating Model-Based Planning and Planner Amortization for Continuous Control

GNN is a Counter? Revisiting GNN for Question Answering

Gradient Step Denoiser for convergent Plug-and-Play

Planning in Stochastic Environments with a Learned Model

Creating Training Sets via Weak Indirect Supervision

Frame Averaging for Invariant and Equivariant Network Design

Taming Sparsely Activated Transformer with Stochastic Experts

From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness

On Non-Random Missing Labels in Semi-Supervised Learning

PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication

QUERY EFFICIENT DECISION BASED SPARSE ATTACKS AGAINST BLACK-BOX DEEP LEARNING MODELS

Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective

EViT: Expediting Vision Transformers via Token Reorganizations

Understanding Intrinsic Robustness Using Label Uncertainty

Label Encoding for Regression Networks

Knowledge Infused Decoding

Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers

Provably Robust Adversarial Examples

A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model

Sparsity Winning Twice: Better Robust Generalization from More Efficient Training

Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing

Conditional Image Generation by Conditioning Variational Auto-Encoders

Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation

Generalized Decision Transformer for Offline Hindsight Information Matching

SUMNAS: Supernet with Unbiased Meta-Features for Neural Architecture Search

CrossMatch: Cross-Classifier Consistency Regularization for Open-Set Single Domain Generalization

Imitation Learning from Observations under Transition Model Disparity

LOSSY COMPRESSION WITH DISTRIBUTION SHIFT AS ENTROPY CONSTRAINED OPTIMAL TRANSPORT

How Did the Model Change? Efficiently Assessing Machine Learning API Shifts

Semi-relaxed Gromov-Wasserstein divergence and applications on graphs

On Bridging Generic and Personalized Federated Learning for Image Classification

Few-shot Learning via Dirichlet Tessellation Ensemble

Learning to Dequantise with Truncated Flows

Latent Image Animator: Learning to Animate Images via Latent Space Navigation

FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations

Superclass-Conditional Gaussian Mixture Model For Learning Fine-Grained Embeddings

Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling

Environment Predictive Coding for Visual Navigation

An Agnostic Approach to Federated Learning with Class Imbalance

Vision-Based Manipulators Need to Also See from Their Hands

A Program to Build E(N)-Equivariant Steerable CNNs

Deconstructing the Inductive Biases of Hamiltonian Neural Networks

A Zest of LIME: Towards Architecture-Independent Model Distances

W-CTC: a Connectionist Temporal Classification Loss with Wild Cards

DictFormer: Tiny Transformer with Shared Dictionary

PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions

RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning

Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations

iLQR-VAE : control-based learning of input-driven dynamics with applications to neural data

Information Gain Propagation: a New Way to Graph Active Learning with Soft Labels

Efficient Token Mixing for Transformers via Adaptive Fourier Neural Operators

Compositional Training for End-to-End Deep AUC Maximization

FedBABU: Toward Enhanced Representation for Federated Image Classification

Unsupervised Semantic Segmentation by Distilling Feature Correspondences

Efficient and Differentiable Conformal Prediction with General Function Classes

Pseudo Numerical Methods for Diffusion Models on Manifolds

Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspective

Learning Weakly-supervised Contrastive Representations

Fast Model Editing at Scale

DEGREE: Decomposition Based Explanation for Graph Neural Networks

Generalizing Few-Shot NAS with Gradient Matching

Sound Adversarial Audio-Visual Navigation

The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization

Illiterate DALL-E Learns to Compose

Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators

Hindsight is 20/20: Leveraging Past Traversals to Aid 3D Perception

Linking Emergent and Natural Languages via Corpus Transfer

Know Thyself: Transferable Visual Control Policies Through Robot-Awareness

PiCO: Contrastive Label Disambiguation for Partial Label Learning

ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity

Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift

Model-augmented Prioritized Experience Replay

Bridging Recommendation and Marketing via Recurrent Intensity Modeling

Continual Learning with Filter Atom Swapping

One After Another: Learning Incremental Skills for a Changing World

DemoDICE: Offline Imitation Learning with Supplementary Imperfect Demonstrations

Learning to Schedule Learning rate with Graph Neural Networks

How Do Vision Transformers Work?

BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis

Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank?

On Incorporating Inductive Biases into VAEs

Learning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral Similarities

Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework

MCMC Should Mix: Learning Energy-Based Model with Neural Transport Latent Space MCMC

Orchestrated Value Mapping for Reinforcement Learning

Gradient Information Matters in Policy Optimization by Back-propagating through Model

Robust Unlearnable Examples: Protecting Data Privacy Against Adversarial Learning

Evaluating Distributional Distortion in Neural Language Modeling

Mapping Language Models to Grounded Conceptual Spaces

UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning

On Robust Prefix-Tuning for Text Classification

Regularized Autoencoders for Isometric Representation Learning

Learning to Generalize across Domains on Single Test Samples

Relational Multi-Task Learning: Modeling Relations between Data and Tasks

ConFeSS: A Framework for Single Source Cross-Domain Few-Shot Learning

GeneDisco: A Benchmark for Experimental Design in Drug Discovery

Scene Transformer: A unified architecture for predicting future trajectories of multiple agents

Simple GNN Regularisation for 3D Molecular Property Prediction and Beyond

How Well Does Self-Supervised Pre-Training Perform with Streaming Data?

Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning

Group-based Interleaved Pipeline Parallelism for Large-scale DNN Training

Practical Integration via Separable Bijective Networks

Switch to Generalize: Domain-Switch Learning for Cross-Domain Few-Shot Classification

Local Feature Swapping for Generalization in Reinforcement Learning

Language modeling via stochastic processes

Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution

Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks

F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization

Neural Relational Inference with Node-Specific Information

DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning

Training Data Generating Networks: Shape Reconstruction via Bi-level Optimization

GraphENS: Neighbor-Aware Ego Network Synthesis for Class-Imbalanced Node Classification

Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph

Using Graph Representation Learning with Schema Encoders to Measure the Severity of Depressive Symptoms

Hot-Refresh Model Upgrades with Regression-Free Compatible Training in Image Retrieval

Graph Auto-Encoder via Neighborhood Wasserstein Reconstruction

Neural Deep Equilibrium Solvers

Relational Surrogate Loss Learning

Graph-Enhanced Exploration for Goal-oriented Reinforcement Learning

Conditioning Sequence-to-sequence Networks with Learned Activations

Inductive Relation Prediction Using Analogy Subgraph Embeddings

Continual Normalization: Rethinking Batch Normalization for Online Continual Learning

Divergence-aware Federated Self-Supervised Learning

Controlling the Complexity and Lipschitz Constant improves Polynomial Nets

Generative Principal Component Analysis

Learning Towards The Largest Margins

Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design

Domain Adversarial Training: A Game Perspective

On the Uncomputability of Partition Functions in Energy-Based Sequence Models

Towards Model Agnostic Federated Learning Using Knowledge Distillation

Minimax Optimization with Smooth Algorithmic Adversaries

A Loss Curvature Perspective on Training Instabilities of Deep Learning Models

Backdoor Defense via Decoupling the Training Process

Learnability Lock: Authorized Learnability Control Through Adversarial Invertible Transformations

On Redundancy and Diversity in Cell-based Neural Architecture Search

Coordination Among Neural Modules Through a Shared Global Workspace

RotoGrad: Gradient Homogenization in Multitask Learning

cosFormer: Rethinking Softmax In Attention

Exploring the Limits of Large Scale Pre-training

Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning

KL Guided Domain Adaptation

ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind

Map Induction: Compositional spatial submap learning for efficient exploration in novel environments

Proving the Lottery Ticket Hypothesis for Convolutional Neural Networks

Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions

Meta-Learning with Fewer Tasks through Task Interpolation

Transformer-based Transform Coding

BEiT: BERT Pre-Training of Image Transformers

Zero Pixel Directional Boundary by Vector Transform

Gaussian Mixture Convolution Networks

Image BERT Pre-training with Online Tokenizer

Online Coreset Selection for Rehearsal-based Continual Learning

Non-Linear Operator Approximations for Initial Value Problems

Better Supervisory Signals by Observing Learning Paths

Bag of Instances Aggregation Boosts Self-supervised Distillation

Omni-Dimensional Dynamic Convolution

Learning State Representations via Retracing in Reinforcement Learning

The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training

Learning to Map for Active Semantic Goal Navigation

Transfer RL across Observation Feature Spaces via Model-Based Regularization

CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing

Adversarial Support Alignment

Boosting the Certified Robustness of L-infinity Distance Nets

Spanning Tree-based Graph Generation for Molecules

Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound

Policy improvement by planning with Gumbel

Learning Scenario Representation for Solving Two-stage Stochastic Integer Programs

Measuring CLEVRness: Black-box Testing of Visual Reasoning Models

Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation

Subspace Regularizers for Few-Shot Class Incremental Learning

Structure-Aware Transformer Policy for Inhomogeneous Multi-Task Reinforcement Learning

Learning Super-Features for Image Retrieval

Auto-scaling Vision Transformers without Training

Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond

NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training

L0-Sparse Canonical Correlation Analysis

Exploiting Class Activation Value for Partial-Label Learning

Dual Lottery Ticket Hypothesis

Visual Representation Learning over Latent Domains

Towards Building A Group-based Unsupervised Representation Disentanglement Framework

Benchmarking the Spectrum of Agent Capabilities

Self-ensemble Adversarial Training for Improved Robustness

Learning Prototype-oriented Set Representations for Meta-Learning

Neural Program Synthesis with Query

Peek-a-Boo: What (More) is Disguised in a Randomly Weighted Neural Network, and How to Find It Efficiently

Coherence-based Label Propagation over Time Series for Accelerated Active Learning

Scaling Laws for Neural Machine Translation

Interacting Contour Stochastic Gradient Langevin Dynamics

GDA-AM: ON THE EFFECTIVENESS OF SOLVING MIN-IMAX OPTIMIZATION VIA ANDERSON MIXING

Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANs

Evolutionary Diversity Optimization with Clustering-based Selection for Reinforcement Learning

Adversarial Robustness Through the Lens of Causality

Stochastic Training is Not Necessary for Generalization

Conditional Object-Centric Learning from Video

Distributionally Robust Models with Parametric Likelihood Ratios

Connectome-constrained Latent Variable Model of Whole-Brain Neural Activity

Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks

Igeood: An Information Geometry Approach to Out-of-Distribution Detection

The Rich Get Richer: Disparate Impact of Semi-Supervised Learning

GiraffeDet: A Heavy-Neck Paradigm for Object Detection

Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning

Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning

$\pi$BO: Augmenting Acquisition Functions with User Beliefs for Bayesian Optimization

R4D: Utilizing Reference Objects for Long-Range Distance Estimation

RegionViT: Regional-to-Local Attention for Vision Transformers

Efficient Computation of Deep Nonlinear Infinite-Width Neural Networks that Learn Features

Efficient Active Search for Combinatorial Optimization Problems

No One Representation to Rule Them All: Overlapping Features of Training Methods

Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization

Deep Attentive Variational Inference

Towards Empirical Sandwich Bounds on the Rate-Distortion Function

Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurring

Data Efficient Language-Supervised Zero-Shot Recognition with Optimal Transport Distillation

Unsupervised Discovery of Object Radiance Fields

A Class of Short-term Recurrence Anderson Mixing Methods and Their Applications

Efficient Self-supervised Vision Transformers for Representation Learning

On the Role of Neural Collapse in Transfer Learning

Optimization and Adaptive Generalization of Three layer Neural Networks

On the Importance of Firth Bias Reduction in Few-Shot Classification

Memorizing Transformers

On the role of population heterogeneity in emergent communication

Plant 'n' Seek: Can You Find the Winning Ticket?

Neural Stochastic Dual Dynamic Programming

Discrete Representations Strengthen Vision Transformer Robustness

You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks

Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization

GPT-Critic: Offline Reinforcement Learning for End-to-End Task-Oriented Dialogue Systems

Bootstrapped Meta-Learning

Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localization

Efficient Sharpness-aware Minimization for Improved Training of Neural Networks

Bandit Learning with Joint Effect of Incentivized Sampling, Delayed Sampling Feedback, and Self-Reinforcing User Preferences

Efficient Neural Causal Discovery without Acyclicity Constraints

Path Auxiliary Proposal for MCMC in Discrete Space

PI3NN: Out-of-distribution-aware Prediction Intervals from Three Neural Networks

Approximation and Learning with Deep Convolutional Models: a Kernel Perspective

Fairness Guarantees under Demographic Shift

Do deep networks transfer invariances across classes?

Resolving Training Biases via Influence-based Data Relabeling

Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage

On feature learning in neural networks with global convergence guarantees

Case-based reasoning for better generalization in textual reinforcement learning

Assessing Generalization of SGD via Disagreement

Churn Reduction via Distillation

Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits

Finding an Unsupervised Image Segmenter in each of your Deep Generative Models

PAC Prediction Sets Under Covariate Shift

FP-DETR: Detection Transformer Advanced by Fully Pre-training

Generalized Kernel Thinning

Graph Neural Network Guided Local Search for the Traveling Salesperson Problem

Toward Efficient Low-Precision Training: Data Format Optimization and Hysteresis Quantization

Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations

Amortized Implicit Differentiation for Stochastic Bilevel Optimization

Neural Models for Output-Space Invariance in Combinatorial Problems

Memory Augmented Optimizers for Deep Learning

Tracking the risk of a deployed model and detecting harmful distribution shifts

ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning

Learning-Augmented $k$-means Clustering

Latent Variable Sequential Set Transformers for Joint Multi-Agent Motion Prediction

It Takes Four to Tango: Multiagent Self Play for Automatic Curriculum Generation

Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation

Spike-inspired rank coding for fast and accurate recurrent neural networks

Attention-based Interpretability with Concept Transformers

Information-theoretic Online Memory Selection for Continual Learning

On Improving Adversarial Transferability of Vision Transformers

Programmatic Reinforcement Learning without Oracles

CADDA: Class-wise Automatic Differentiable Data Augmentation for EEG Signals

Understanding and Improving Graph Injection Attack by Promoting Unnoticeability

Learning transferable motor skills with hierarchical latent mixture policies

Responsible Disclosure of Generative Models Using Scalable Fingerprinting

A Fine-Tuning Approach to Belief State Modeling

Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach

Learning to Annotate Part Segmentation with Gradient Matching

Collapse by Conditioning: Training Class-conditional GANs with Limited Data

Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks

DriPP: Driven Point Processes to Model Stimuli Induced Patterns in M/EEG Signals

Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysis

On the Certified Robustness for Ensemble Models and Beyond

Visual hyperacuity with moving sensor and recurrent neural computations

Implicit Bias of Projected Subgradient Method Gives Provable Robust Recovery of Subspaces of Unknown Codimension

CLEVA-Compass: A Continual Learning Evaluation Assessment Compass to Promote Research Transparency and Comparability

GRAND++: Graph Neural Diffusion with A Source Term

Can an Image Classifier Suffice For Action Recognition?

AS-MLP: An Axial Shifted MLP Architecture for Vision

Fairness in Representation for Multilingual NLP: Insights from Controlled Experiments on Conditional Language Modeling

MT3: Multi-Task Multitrack Music Transcription

Information Prioritization through Empowerment in Visual Model-based RL

VOS: Learning What You Don't Know by Virtual Outlier Synthesis

Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off

Pre-training Molecular Graph Representation with 3D Geometry

A General Analysis of Example-Selection for Stochastic Gradient Descent

Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification

Objects in Semantic Topology

Neural Spectral Marked Point Processes

Demystifying Limited Adversarial Transferability in Automatic Speech Recognition Systems

Label-Efficient Semantic Segmentation with Diffusion Models

EXACT: Scalable Graph Neural Networks Training via Extreme Activation Compression

Improving Mutual Information Estimation with Annealed and Energy-Based Bounds

An Autoregressive Flow Model for 3D Molecular Geometry Generation from Scratch

Learning Curves for Gaussian Process Regression with Power-Law Priors and Targets

Differentiable Gradient Sampling for Learning Implicit 3D Scene Reconstructions from a Single Image

Tighter Sparse Approximation Bounds for ReLU Neural Networks

The Uncanny Similarity of Recurrence and Depth

A Deep Variational Approach to Clustering Survival Data

Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?

A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning

Continuous-Time Meta-Learning with Forward Mode Differentiation

Geometric Transformers for Protein Interface Contact Prediction

Who Is Your Right Mixup Partner in Positive and Unlabeled Learning

Generative Modeling with Optimal Transport Maps

MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining

Maximizing Ensemble Diversity in Deep Reinforcement Learning

ADAVI: Automatic Dual Amortized Variational Inference Applied To Pyramidal Bayesian Models

Monotonic Differentiable Sorting Networks

Interpretable Unsupervised Diversity Denoising and Artefact Removal

FedPara: Low-rank Hadamard Product for Communication-Efficient Federated Learning

Trivial or Impossible --- dichotomous data difficulty masks model differences (on ImageNet and beyond)

Neural Contextual Bandits with Deep Representation and Shallow Exploration

Learning Neural Contextual Bandits through Perturbed Rewards

Multi-Task Processes

The Role of Pretrained Representations for the OOD Generalization of RL Agents

Differentially Private Fine-tuning of Language Models

Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy

QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization

Resonance in Weight Space: Covariate Shift Can Drive Divergence of SGD with Momentum

Stiffness-aware neural network for learning Hamiltonian systems

Topological Graph Neural Networks

CoordX: Accelerating Implicit Neural Representation with a Split MLP Architecture

Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality

Meta Learning Low Rank Covariance Factors for Energy Based Deterministic Uncertainty

Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations

Sample and Computation Redistribution for Efficient Face Detection

How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective

Closed-form Sample Probing for Learning Generative Models in Zero-shot Learning

Dive Deeper Into Integral Pose Regression

MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer

On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning

SHINE: SHaring the INverse Estimate from the forward pass for bi-level optimization and implicit models

Leveraging Automated Unit Tests for Unsupervised Code Translation

Explainable GNN-Based Models over Knowledge Graphs

Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing

DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization

SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations

IntSGD: Adaptive Floatless Compression of Stochastic Gradients

Understanding the Role of Self Attention for Efficient Speech Recognition

PAC-Bayes Information Bottleneck

When should agents explore?

Understanding and Leveraging Overparameterization in Recursive Value Estimation

Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path

Hindsight: Posterior-guided training of retrievers for improved open-ended generation

Imbedding Deep Neural Networks

PF-GNN: Differentiable particle filtering based approximation of universal graph representations

Mirror Descent Policy Optimization

Unrolling PALM for Sparse Semi-Blind Source Separation

MoReL: Multi-omics Relational Learning

Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity

Hybrid Local SGD for Federated Learning with Heterogeneous Communications

How to Train Your MAML to Excel in Few-Shot Classification

Learning more skills through optimistic exploration

Understanding and Preventing Capacity Loss in Reinforcement Learning

Dealing with Non-Stationarity in MARL via Trust-Region Decomposition

Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics

Cross-Domain Imitation Learning via Optimal Transport

Prototypical Contrastive Predictive Coding

LoRA: Low-Rank Adaptation of Large Language Models

Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks

Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning

Optimizing Neural Networks with Gradient Lexicase Selection

Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

Value Gradient weighted Model-Based Reinforcement Learning

Learning Value Functions from Undirected State-only Experience

Vector-quantized Image Modeling with Improved VQGAN

Toward Faithful Case-based Reasoning through Learning Prototypes in a Nearest Neighbor-friendly Space.

Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism

Transformers Can Do Bayesian Inference

Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space

Network Augmentation for Tiny Deep Learning

Optimal Transport for Causal Discovery

GLASS: GNN with Labeling Tricks for Subgraph Representation Learning

New Insights on Reducing Abrupt Representation Change in Online Continual Learning

Decoupled Adaptation for Cross-Domain Object Detection

No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models

Visual Correspondence Hallucination

Bayesian Framework for Gradient Leakage

Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization

Learning curves for continual learning in neural networks: Self-knowledge transfer and forgetting

How many degrees of freedom do we need to train deep networks: a loss landscape perspective

Effective Model Sparsification by Scheduled Grow-and-Prune Methods

Finite-Time Convergence and Sample Complexity of Multi-Agent Actor-Critic Reinforcement Learning with Average Reward

Energy-Inspired Molecular Conformation Optimization

An Explanation of In-context Learning as Implicit Bayesian Inference

The Close Relationship Between Contrastive Learning and Meta-Learning

Learning Transferable Reward for Query Object Localization with Policy Adaptation

Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis--Hastings

You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction

Shuffle Private Stochastic Convex Optimization

Maximum Entropy RL (Provably) Solves Some Robust RL Problems

Wiring Up Vision: Minimizing Supervised Synaptic Updates Needed to Produce a Primate Ventral Stream

Autonomous Learning of Object-Centric Abstractions for High-Level Planning

Fortuitous Forgetting in Connectionist Networks

A Generalized Weighted Optimization Method for Computational Learning and Inversion

Learning Synthetic Environments and Reward Networks for Reinforcement Learning

What Makes Better Augmentation Strategies? Augment Difficult but Not too Different

Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling

FILM: Following Instructions in Language with Modular Methods

T-WaveNet: A Tree-Structured Wavelet Neural Network for Time Series Signal Analysis

Top-label calibration and multiclass-to-binary reductions

PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning

Leveraging unlabeled data to predict out-of-distribution performance

On the Limitations of Multimodal VAEs

Maximum n-times Coverage for Vaccine Design

Does your graph need a confidence boost? Convergent boosted smoothing on graphs with tabular node features

TRAIL: Near-Optimal Imitation Learning with Suboptimal Data

The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs

A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features

Recursive Disentanglement Network

Givens Coordinate Descent Methods for Rotation Matrix Learning in Trainable Embedding Indexes

Multi-objective Optimization by Learning Space Partition

Neural Structured Prediction for Inductive Node Classification

Knowledge Removal in Sampling-based Bayesian Inference

Einops: Clear and Reliable Tensor Manipulations with Einstein-like Notation

Language-biased image classification: evaluation based on semantic representations

What’s Wrong with Deep Learning in Tree Search for Combinatorial Optimization

Convergent and Efficient Deep Q Learning Algorithm

Constrained Policy Optimization via Bayesian World Models

Quadtree Attention for Vision Transformers

FastSHAP: Real-Time Shapley Value Estimation

Robust and Scalable SDE Learning: A Functional Perspective

CURVATURE-GUIDED DYNAMIC SCALE NETWORKS FOR MULTI-VIEW STEREO

StyleAlign: Analysis and Applications of Aligned StyleGAN Models

Autonomous Reinforcement Learning: Formalism and Benchmarking

Understanding over-squashing and bottlenecks on graphs via curvature

Exploring extreme parameter compression for pre-trained language models

Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks

Pix2seq: A Language Modeling Framework for Object Detection

AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis

Scale Efficiently: Insights from Pretraining and Finetuning Transformers

Noisy Feature Mixup

Pretrained Language Model in Continual Learning: A Comparative Study

Fooling Explanations in Text Classifiers

Large Language Models Can Be Strong Differentially Private Learners

Data Poisoning Won’t Save You From Facial Recognition

Adaptive Wavelet Transformer Network for 3D Shape Representation Learning

Evidential Turing Processes

Invariant Causal Representation Learning for Out-of-Distribution Generalization

Enhancing Cross-lingual Transfer by Manifold Mixup

Why Propagate Alone? Parallel Use of Labels and Features on Graphs

Progressive Distillation for Fast Sampling of Diffusion Models

Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teaming

How Low Can We Go: Trading Memory for Error in Low-Precision Training

Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective

Active Hierarchical Exploration with Stable Subgoal Representation Learning

SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning

Permutation-Based SGD: Is Random Optimal?

Towards Continual Knowledge Learning of Language Models

GeoDiff: A Geometric Diffusion Model for Molecular Conformation Generation

Learning to Complete Code with Sketches

Dynamic Token Normalization improves Vision Transformers

Evaluation Metrics for Graph Generative Models: Problems, Pitfalls, and Practical Solutions

Learning Discrete Structured Variational Auto-Encoder using Natural Evolution Strategies

Memory Replay with Data Compression for Continual Learning

VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects

Goal-Directed Planning via Hindsight Experience Replay

NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs

On the Convergence of mSGD and AdaGrad for Stochastic Optimization

Hybrid Random Features

Domino: Discovering Systematic Errors with Cross-Modal Embeddings

Learned Simulators for Turbulence

Scalable Sampling for Nonsymmetric Determinantal Point Processes

Deep AutoAugment

Towards Understanding the Robustness Against Evasion Attack on Categorical Data

Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies

Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme

Auto-Transfer: Learning to Route Transferable Representations

Hierarchical Few-Shot Imitation with Skill Transition Models

How Attentive are Graph Attention Networks?

FairCal: Fairness Calibration for Face Verification

Provably convergent quasistatic dynamics for mean-field two-player zero-sum games

ProtoRes: Proto-Residual Network for Pose Authoring via Learned Inverse Kinematics

Sparse Attention with Learning to Hash

Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations

AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning

Optimizer Amalgamation

Entroformer: A Transformer-based Entropy Model for Learned Image Compression

Continual Learning with Recursive Gradient Optimization

HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation

OntoProtein: Protein Pretraining With Gene Ontology Embedding

Permutation Compressors for Provably Faster Distributed Nonconvex Optimization

CrossBeam: Learning to Search in Bottom-Up Program Synthesis

RvS: What is Essential for Offline RL via Supervised Learning?

Learning Continuous Environment Fields via Implicit Functions

Fast AdvProp

Revisiting flow generative models for Out-of-distribution detection

DISCOVERING AND EXPLAINING THE REPRESENTATION BOTTLENECK OF DNNS

SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning

Parallel Training of GRU Networks with a Multi-Grid Solver for Long Sequences

Poisoning and Backdooring Contrastive Learning

iFlood: A Stable and Effective Regularizer

Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction

Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients

When, Why, and Which Pretrained GANs Are Useful?

Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver

RelaxLoss: Defending Membership Inference Attacks without Losing Utility

Compositional Attention: Disentangling Search and Retrieval

Anomaly Detection for Tabular Data with Internal Contrastive Learning

Variational Inference for Discriminative Learning with Generative Modeling of Feature Incompletion

Stability Regularization for Discrete Representation Learning

Fixed Neural Network Steganography: Train the images, not the network

Bregman Gradient Policy Optimization

X-model: Improving Data Efficiency in Deep Learning with A Minimax Model

Low-Budget Active Learning via Wasserstein Distance: An Integer Programming Approach

Target-Side Input Augmentation for Sequence to Sequence Generation

Graph Condensation for Graph Neural Networks

GreaseLM: Graph REASoning Enhanced Language Models

Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics

MonoDistill: Learning Spatial Features for Monocular 3D Object Detection

Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL

Language-driven Semantic Segmentation

Constructing Orthogonal Convolutions in an Explicit Manner

HTLM: Hyper-Text Pre-Training and Prompting of Language Models

Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting

BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models

Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks

Neural Methods for Logical Reasoning over Knowledge Graphs

Data-Driven Offline Optimization for Architecting Hardware Accelerators

Towards Better Understanding and Better Generalization of Low-shot Classification in Histology Images with Contrastive Learning

Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios

Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios

Learning Versatile Neural Architectures by Propagating Network Codes

A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning

Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization

Dynamics-Aware Comparison of Learned Reward Functions

In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications

Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?

Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future

Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching

Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations

Sound and Complete Neural Network Repair with Minimality and Locality Guarantees

Discriminative Similarity for Data Clustering

Generalized Demographic Parity for Group Fairness

Blaschke Product Neural Networks (BPNN): A Physics-Infused Neural Network for Phase Retrieval of Meromorphic Functions

StyleNeRF: A Style-based 3D Aware Generator for High-resolution Image Synthesis

Distribution Compression in Near-Linear Time

On the Connection between Local Attention and Dynamic Depth-wise Convolution

Explanations of Black-Box Models based on Directional Feature Interactions

Language model compression with weighted low-rank factorization

Prototype memory and attention mechanisms for few shot image generation

Surrogate Gap Minimization Improves Sharpness-Aware Training

Optimal Representations for Covariate Shift

Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps

Anytime Dense Prediction with Confidence Adaptivity

Trigger Hunting with a Topological Prior for Trojan Detection

Graph-Guided Network for Irregularly Sampled Multivariate Time Series

SketchODE: Learning neural sketch representation in continuous time

Convergent Graph Solvers

MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling

From Intervention to Domain Transportation: A Novel Perspective to Optimize Recommendation

Concurrent Adversarial Learning for Large-Batch Training

CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention

Properties from mechanisms: an equivariance perspective on identifiable representation learning

A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training

Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory

On the Pitfalls of Analyzing Individual Neurons in Language Models

Graph Neural Networks with Learnable Structural and Positional Representations

Step-unrolled Denoising Autoencoders for Text Generation

Sparse Communication via Mixed Distributions

Chemical-Reaction-Aware Molecule Representation Learning

CrowdPlay: Crowdsourcing Human Demonstrations for Offline Learning

Adversarial Retriever-Ranker for Dense Text Retrieval

Tuformer: Data-driven Design of Transformers for Improved Generalization or Efficiency

Handling Distribution Shifts on Graphs: An Invariance Perspective

Effect of scale on catastrophic forgetting in neural networks

Fast Differentiable Matrix Square Root

Topologically Regularized Data Embeddings

Neural Variational Dropout Processes

Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View

Privacy Implications of Shuffling

Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design

Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information

Proof Artifact Co-Training for Theorem Proving with Language Models

Non-Parallel Text Style Transfer with Self-Parallel Supervision

A global convergence theory for deep ReLU implicit networks via over-parameterization

R5: Rule Discovery with Reinforced and Recurrent Relational Reasoning

Attacking deep networks with surrogate-based adversarial black-box methods is easy

Revisiting Over-smoothing in BERT from the Perspective of Graph

Neural Network Approximation based on Hausdorff distance of Tropical Zonotopes

Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice

VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning

On-Policy Model Errors in Reinforcement Learning

Signing the Supermask: Keep, Hide, Invert

Diverse Client Selection for Federated Learning via Submodular Maximization

Unifying Likelihood-free Inference with Black-box Optimization and Beyond

COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation

Transformer Embeddings of Irregularly Spaced Events and Their Participants

ViDT: An Efficient and Effective Fully Transformer-based Object Detector

NETWORK INSENSITIVITY TO PARAMETER NOISE VIA PARAMETER ATTACK DURING TRAINING

Rethinking Adversarial Transferability from a Data Distribution Perspective

Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks

Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning

Neural graphical modelling in continuous-time: consistency guarantees and algorithms

Capturing Structural Locality in Non-parametric Language Models

Distilling GANs with Style-Mixed Triplets for X2I Translation with Limited Data

EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits

On the Existence of Universal Lottery Tickets

Sampling with Mirrored Stein Operators

A Statistical Framework for Efficient Out of Distribution Detection in Deep Neural Networks

Discovering Latent Concepts Learned in BERT

Provable Adaptation across Multiway Domains via Representation Learning

Temporal Alignment Prediction for Supervised Representation Learning and Few-Shot Sequence Classification

Group equivariant neural posterior estimation

Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration

Phase Collapse in Neural Networks

Federated Learning from Only Unlabeled Data with Class-conditional-sharing Clients

Message Passing Neural PDE Solvers

It Takes Two to Tango: Mixup for Deep Metric Learning

Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games

Self-supervised Learning is More Robust to Dataset Imbalance

Contrastive Clustering to Mine Pseudo Parallel Data for Unsupervised Translation

A fast and accurate splitting method for optimal transport: analysis and implementation

Task-Induced Representation Learning

Triangle and Four Cycle Counting with Predictions in Graph Streams

ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods

How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis

Expressiveness and Approximation Properties of Graph Neural Networks

How to deal with missing data in supervised deep learning?

Possibility Before Utility: Learning And Using Hierarchical Affordances

Autoregressive Diffusion Models

Expressivity of Emergent Languages is a Trade-off between Contextual Complexity and Unpredictability

Actor-Critic Policy Optimization in a Large-Scale Imperfect-Information Game

Fast Regression for Structured Inputs

Learning Efficient Online 3D Bin Packing on Packing Configuration Trees

Learning Long-Term Reward Redistribution via Randomized Return Decomposition

Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks

Learning Strides in Convolutional Neural Networks

Data-Efficient Graph Grammar Learning for Molecular Generation

Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect

Certified Robustness for Deep Equilibrium Models via Interval Bound Propagation

On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications

ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity

Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality

Explaining Point Processes by Learning Interpretable Temporal Logic Rules

On Evaluation Metrics for Graph Generative Models

Probabilistic Implicit Scene Completion

Training Structured Neural Networks Through Manifold Identification and Variance Reduction

Natural Language Descriptions of Deep Features

Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, And No Retraining

Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers

Visual Representation Learning Does Not Generalize Strongly Within the Same Domain

miniF2F: a cross-system benchmark for formal Olympiad-level mathematics

Controlling Directions Orthogonal to a Classifier

Pareto Policy Pool for Model-based Offline Reinforcement Learning

Learning a subspace of policies for online adaptation in Reinforcement Learning

Neural Parameter Allocation Search

A Unified Wasserstein Distributional Robustness Framework for Adversarial Training

Fair Normalizing Flows

Self-Joint Supervised Learning

BiBERT: Accurate Fully Binarized BERT

LIGS: Learnable Intrinsic-Reward Generation Selection for Multi-Agent Learning

An Unconstrained Layer-Peeled Perspective on Neural Collapse

Hierarchical Variational Memory for Few-shot Learning Across Domains

Scarf: Self-Supervised Contrastive Learning using Random Feature Corruption

What Happens after SGD Reaches Zero Loss? --A Mathematical Framework

Symbolic Learning to Optimize: Towards Interpretability and Scalability

PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior

Revisit Kernel Pruning with Lottery Regulated Grouped Convolutions

Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting

Improving Non-Autoregressive Translation Models Without Distillation

Evaluating Disentanglement of Structured Representations

Sqrt(d) Dimension Dependence of Langevin Monte Carlo

Neural Solvers for Fast and Accurate Numerical Optimal Control

Comparing Distributions by Measuring Differences that Affect Decision Making

Graph-less Neural Networks: Teaching Old MLPs New Tricks Via Distillation

Score-Based Generative Modeling with Critically-Damped Langevin Diffusion

Learning by Directional Gradient Descent

Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery

An Information Fusion Approach to Learning with Instance-Dependent Label Noise

Joint Shapley values: a measure of joint feature importance

Weighted Training for Cross-Task Learning

Adversarial Unlearning of Backdoors via Implicit Hypergradient

Pareto Set Learning for Neural Multi-Objective Combinatorial Optimization

Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space

Learning Representation from Neural Fisher Kernel with Low-rank Approximation

Actor-critic is implicitly biased towards high entropy optimal policies

Self-Supervised Inference in State-Space Models

Overcoming The Spectral Bias of Neural Value Approximation

Automatic Loss Function Search for Predict-Then-Optimize Problems with Strong Ranking Property

IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor Scenes

Learning to Extend Molecular Scaffolds with Structural Motifs

Lossless Compression with Probabilistic Circuits

SGD Can Converge to Local Maxima

Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings

Meta-Imitation Learning by Watching Video Demonstrations

WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection

Differentiable DAG Sampling

Hyperparameter Tuning with Renyi Differential Privacy

Understanding approximate and unrolled dictionary learning for pattern recovery

Constraining Linear-chain CRFs to Regular Languages

Conditional Contrastive Learning with Kernel

Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descent

Imitation Learning by Reinforcement Learning

Multi-Agent MDP Homomorphic Networks

Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation

Nonlinear ICA Using Volume-Preserving Transformations

Online Hyperparameter Meta-Learning with Hypergradient Distillation

Relating transformers to models and neural representations of the hippocampal formation

Ab-Initio Potential Energy Surfaces by Pairing GNNs with Neural Wave Functions

Bayesian Neural Network Priors Revisited

AdaAug: Learning Class- and Instance-adaptive Data Augmentation Policies

Procedural generalization by planning with self-supervised world models

EigenGame Unloaded: When playing games is better than optimizing

End-to-End Learning of Probabilistic Hierarchies on Graphs

Asymmetry Learning for Counterfactually-invariant Classification in OOD Tasks

Dropout Q-Functions for Doubly Efficient Reinforcement Learning

Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection

DeSKO: Stability-Assured Robust Control with a Deep Stochastic Koopman Operator

Differentially Private Fractional Frequency Moments Estimation with Polylogarithmic Space

On the Optimal Memorization Power of ReLU Neural Networks

Model Agnostic Interpretability for Multiple Instance Learning

GNN-LM: Language Modeling based on Global Contexts via GNN

Fast Generic Interaction Detection for Model Interpretability and Compression

Towards Understanding the Data Dependency of Mixup-style Training

DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting

Safe Neurosymbolic Learning with Differentiable Symbolic Execution

Gradient Importance Learning for Incomplete Observations

A Biologically Interpretable Graph Convolutional Network to Link Genetic Risk Pathways and Imaging Phenotypes of Disease

Equivariant Subgraph Aggregation Networks

CoBERL: Contrastive BERT for Reinforcement Learning

Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs

Unsupervised Disentanglement with Tensor Product Representations on the Torus

Multi-Mode Deep Matrix and Tensor Factorization

Zero-Shot Self-Supervised Learning for MRI Reconstruction

NASPY: Automated Extraction of Automated Machine Learning Models

LEARNING GUARANTEES FOR GRAPH CONVOLUTIONAL NETWORKS ON THE STOCHASTIC BLOCK MODEL

Should I Run Offline Reinforcement Learning or Behavioral Cloning?

Mention Memory: incorporating textual knowledge into Transformers through entity mention attention

Learning Features with Parameter-Free Layers

Multi-Critic Actor Learning: Teaching RL Policies to Act with Style

GradMax: Growing Neural Networks using Gradient Information

Critical Points in Quantum Generative Models

ComPhy: Compositional Physical Reasoning of Objects and Events from Videos

Transferable Adversarial Attack based on Integrated Gradients

DKM: Differentiable k-Means Clustering Layer for Neural Network Compression

Scale Mixtures of Neural Network Gaussian Processes

Reward Uncertainty for Exploration in Preference-based Reinforcement Learning

Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domains

Policy Smoothing for Provably Robust Reinforcement Learning

FlexConv: Continuous Kernel Convolutions With Differentiable Kernel Sizes

CKConv: Continuous Kernel Convolution For Sequential Data

RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation

On the Convergence of Certified Robust Training with Interval Bound Propagation

Rethinking Goal-Conditioned Supervised Learning and Its Connection to Offline RL

Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models

On Distributed Adaptive Optimization with Gradient Compression

Sequence Approximation using Feedforward Spiking Neural Network for Spatiotemporal Learning: Theory and Optimization Methods

Zero-CL: Instance and Feature decorrelation for negative-free symmetric contrastive learning

Salient ImageNet: How to discover spurious features in Deep Learning?

Differentiable Expectation-Maximization for Set Representation Learning

Offline Reinforcement Learning with Implicit Q-Learning

Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks