ICLR 2016

May 2 - 4, 2016

Caribe Hilton, San Juan, Puerto Rico

We recommend landing at the Luis Munoz Marin International Airport. The best way to get from this airport to the hotel is by taxi, which is about a 15 minute drive and costs around $20.

Important: Local transmission of the Zika virus has been reported in Puerto Rico. While in most cases the symptoms of Zika are mild, women who are pregnant and women and men who may conceive a child in the near future have more reason to be concerned about the virus.

The US Centers for Disease Control have reliable and current information on the Zika virus here:

http://www.cdc.gov/zika/

We recommend that anyone with concerns about Zika virus review this information.

For instructions on the submission process, go here.

For instructions on the submission process, go here.

To register and make hotel reservations, go here.

On the day of the meeting, come pick up your badge at the Grand Salon Los Rosales, which is right next to the hotel (ask the staff of the hotel for more directions).

network: hmeeting
password: iclr16

Talks are now available on videolectures.net:

http://videolectures.net/iclr2016_san_juan/

https://www.facebook.com/iclr.cc

We've created a poll to gather feedback and suggestions on ICLR:

https://www.facebook.com/events/1737067246550684/permalink/1737070989883643/

Please participate by upvoting the suggestions you like or adding your own suggestions.

Hugo Larochelle, Twitter and Université de Sherbrooke

Samy Bengio, Google
Brian Kingsbury, IBM Watson Group

Yoshua Bengio, Université de Montreal
Yann LeCun, New York University and Facebook

Ryan Adams, Twitter and Harvard
Antoine Bordes, Facebook
KyungHyun Cho, New York University
Adam Coates, Baidu
Aaron Courville, Université de Montréal
Trevor Darrell, University of California, Berkeley
Ian Goodfellow, Google
Roger Grosse, University of Toronto
Nicolas Le Roux, Criteo
Honglak Lee, University of Michigan
Julien Mairal, INRIA
Chris Manning, Stanford University
Roland Memisevic, Université de Montréal
Joelle Pineau, McGill University
John Platt, Google
Marc'Aurelio Ranzato, Facebook
Tara Sainath, Google
Ruslan Salakhutdinov, University of Toronto
Raquel Urtasun, University of Toronto

iclr2016.programchairs@gmail.com

We are currently taking sponsorship applications for ICLR 2016. Companies interested in sponsoring should contact us at iclr2016.programchairs@gmail.com.

Deep Robotic Learning

The problem of building an autonomous robot has traditionally been viewed as one of integration: connecting together modular components, each one designed to handle some portion of the perception and decision making process. For example, a vision system might be connected to a planner that might in turn provide commands to a low-level controller that drives the robot's motors. In this talk, I will discuss how ideas from deep learning can allow us to build robotic control mechanisms that combine both perception and control into a single system. This system can then be trained end-to-end on the task at hand. I will show how this end-to-end approach actually simplifies the perception and control problems, by allowing the perception and control mechanisms to adapt to one another and to the task. I will also present some recent work on scaling up deep robotic learning on a cluster consisting of multiple robotic arms, and demonstrate results for learning grasping strategies that involve continuous feedback and hand-eye coordination using deep convolutional neural networks.

BIO: Sergey Levine is an assistant professor at the University of Washington. His research focuses on robotics and machine learning. In his PhD thesis, he developed a novel guided policy search algorithm for learning complex neural network control policies, which was later applied to enable a range of robotic tasks, including end-to-end training of policies for perception and control. He has also developed algorithms for learning from demonstration, inverse reinforcement learning, efficient training of stochastic neural networks, computer vision, and data-driven character animation.

Should Model Architecture Reflect Linguistic Structure?

Sequential recurrent neural networks (RNNs) over finite alphabets are remarkably effective models of natural language. RNNs now obtain language modeling results that substantially improve over long-standing state-of-the-art baselines, as well as in various conditional language modeling tasks such as machine translation, image caption generation, and dialogue generation. Despite these impressive results, such models are a priori inappropriate models of language. One point of criticism is that language users create and understand new words all the time, challenging the finite vocabulary assumption. A second is that relationships among words are computed in terms of latent nested structures rather than sequential surface order (Chomsky, 1957; Everaert, Huybregts, Chomsky, Berwick, and Bolhuis, 2015).

In this talk I discuss two models that explore the hypothesis that more (a priori) appropriate models of language will lead to better performance on real-world language processing tasks. The first composes sub word units (bytes, characters, or morphemes) into lexical representations, enabling more naturalistic interpretation and generation of novel word forms. The second, which we call recurrent neural network grammars (RNNGs), is a new generative model of sentences that explicitly models nested, hierarchical relationships among words and phrases. RNNGs operate via a recursive syntactic process reminiscent of probabilistic context-free grammar generation, but decisions are parameterized using RNNs that condition on the entire (top-down, left-to-right) syntactic derivation history, greatly relaxing context-free independence assumptions. Experimental results show that RNNGs obtain better results in generating language than models that don’t exploit linguistic structures.

BIO: Chris Dyer is an assistant professor in the Language Technologies Institute and Machine Learning Department at Carnegie Mellon University. He obtained his PhD in Linguistics at the University of Maryland under Philip Resnik in 2010. His work has been nominated for—and occasionally received—best paper awards at EMNLP, NAACL, and ACL.

Guaranteed Non-convex Learning Algorithms through Tensor Factorization

Modern machine learning involves massive datasets of text, images, videos, biological data, and so on. Most learning tasks can be framed as optimization problems which turn out to be non-convex and NP-hard to solve. This hardness barrier can be overcome by: (i) focusing on conditions which make learning tractable, (ii) replacing the given optimization objective with better behaved ones, and (iii) exploiting non-obvious connections that abound in learning problems.

I will discuss the above in the context of: (i) unsupervised learning of latent variable models and (ii) training multi-layer neural networks, through a novel framework involving spectral decomposition of moment matrices and tensors. Tensors are rich structures that can encode higher order relationships in data. Despite being non-convex, tensor decomposition can be solved optimally using simple iterative algorithms under mild conditions. In practice, tensor methods yield enormous gains both in running times and learning accuracy over traditional methods for training probabilistic models such as variational inference. These positive results demonstrate that many challenging learning tasks can be solved efficiently, both in theory and in practice.

BIO: Anima Anandkumar is a faculty at the EECS Dept. at U.C.Irvine since August 2010. Her research interests are in the areas of large-scale machine learning, non-convex optimization and high-dimensional statistics. In particular, she has been spearheading the development and analysis of tensor algorithms for a variety of learning problems. She is the recipient of the Alfred. P. Sloan Fellowship, Microsoft Faculty Fellowship, Google research award, ARO and AFOSR Young Investigator Awards, NSF CAREER Award, Early Career Excellence in Research Award at UCI, Best Thesis Award from the ACM SIGMETRICS society, IBM Fran Allen PhD fellowship, and best paper awards from the ACM SIGMETRICS and IEEE Signal Processing societies. She received her B.Tech in Electrical Engineering from IIT Madras in 2004 and her PhD from Cornell University in 2009. She was a postdoctoral researcher at MIT from 2009 to 2010, and a visiting faculty at Microsoft Research New England in 2012 and 2014. Anima

Beyond Backpropagation: Uncertainty Propagation

Deep learning is founded on composable functions that are structured to capture regularities in data and can have their parameters optimized by backpropagation (differentiation via the chain rule). Their recent success is founded on the increased availability of data and computational power. However, they are not very data efficient. In low data regimes parameters are not well determined and severe overfitting can occur. The solution is to explicitly handle the indeterminacy by converting it to parameter uncertainty and propagating it through the model. Uncertainty propagation is more involved than backpropagation because it involves convolving the composite functions with probability distributions and integration is more challenging than differentiation.

We will present one approach to fitting such models using Gaussian processes. The resulting models perform very well in both supervised and unsupervised learning on small data sets. The remaining challenge is to scale the algorithms to much larger data.

BIO: Neil Lawrence is Professor of Machine Learning at the University of Sheffield. His expertise is in probabilistic modelling with a particular focus on Gaussian processes and a strong interest in bridging the worlds of mechanistic and empirical models.

Title: Incorporating Structure in Deep Learning

Deep learning algorithms attempt to model high-level abstractions of the data using architectures composed of multiple non-linear transformations. A multiplicity of variants have been proposed and shown to be extremely successful in a wide variety of applications including computer vision, speech recognition as well as natural language processing. In this talk I’ll show how to make these representations more powerful by exploiting structure in the outputs, the loss function as well as in the learned embeddings.

Many problems in real-world applications involve predicting several random variables that are statistically related. Graphical models have been typically employed to represent and exploit the output dependencies. However, most current learning algorithms assume that the models are log linear in the parameters. In the first part of the talk I’ll show a variety of algorithms that can learn arbitrary functions while exploiting the output dependencies, unifying deep learning and graphical models.

Supervised training of deep neural nets typically relies on minimizing cross-entropy. However, in many domains, we are interested in performing well on metrics specific to the application domain. In the second part of the talk I’ll show a direct loss minimization approach to train deep neural networks, which provably minimizes the task loss. This is often non-trivial, since these loss functions are neither smooth nor decomposable and thus are not amenable to optimization with standard gradient-based methods. I’ll demonstrate the applicability of this general framework in the context of maximizing average precession, a structured loss commonly used to evaluate ranking problems.

Deep learning has become a very popular approach to learn word, sentence and/or image embeddings. Neural embeddings have shown great performance in tasks such as image captioning, machine translation and paraphrasing. In the last part of my talk I’ll show how to exploit the partial order structure of the visual semantic hierarchy over words, sentences and images to learn order embeddings. I’ll demonstrate the utility of these new representations for hypernym prediction and image-caption retrieval.

BIO: Raquel Urtasun is an Assistant Professor in the Department of Computer Science at the University of Toronto and a Canada Research Chair in Machine Learning and Computer Vision. Prior to this, she was an Assistant Professor at the Toyota Technological Institute at Chicago (TTIC), an academic computer science institute affiliated with the University of Chicago. She received her Ph.D. degree from the Computer Science department at Ecole Polytechnique Federal de Lausanne (EPFL) in 2006 and did her postdoc at MIT and UC Berkeley. Her research interests include machine learning, computer vision and robotics. Her recent work involves perception algorithms for self-driving cars, deep structured models and exploring problems at the intersection of vision and language. She is a recipient of a Ministry of Education and Innovation Early Researcher Award, two Google Faculty Research Awards, a Connaught New Researcher Award and a Best Paper Runner up Prize awarded at the Conference on Computer Vision and Pattern Recognition (CVPR). She is also Program Chair of CVPR 2018, an Editor of the International Journal in Computer Vision (IJCV) and has served as Area Chair of multiple machine learning and vision conferences (i.e., NIPS, UAI, ICML, ICLR, CVPR, ECCV, ICCV).

This year, the program committee has decided to grant two Best Paper Awards to papers that were singled out for their impressive and original scientific contributions.

The recipients of a Best Paper Award for ICLR 2016 are:

• Neural Programmer-Interpreters
  Scott Reed, Nando de Freitas
• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
  Song Han, Huizi Mao, Bill Dally

The selection was made by the program chairs and was informed by the feedback from the reviewers and area chairs.

1. Deep Motif: Visualizing Genomic Sequence Classifications
   Jack Lanchantin, Ritambhara Singh, Zeming Lin, & Yanjun Qi
2. Lookahead Convolution Layer for Unidirectional Recurrent Neural Networks
   Chong Wang, Dani Yogatama, Adam Coates, Tony Han, Awni Hannun, Bo Xiao
3. Joint Stochastic Approximation Learning of Helmoltz Machines
   HaotianXu, Zhijian Ou
4. A Minimalistic Approach to Sum-Product Network Learning for Real Applications
   Viktoriya Krakovna, Moshe Looks
5. Hardware-Oriented Approximation of Convolutional Neural Networks
   Philipp Gysel, Mohammad Motamedi, Soheil Ghiasi
6. Neurogenic Deep Learning
   Timothy J. Draelos, Nadine E. Miner, Jonathan A. Cox, Christopher C. Lamb, Conrad D. James, James B. Aimone
7. Deep Bayesian Neural Nets as Deep Matrix Gaussian Processes
   Christos Louizos, Max Welling
8. Neural Network Training Variations in Speech and Subsequent Performance Evaluation
   Ewout van den Berg, Bhuvana Ramabhadran, Michael Picheny
9. Neural Variational Random Field Learning
   Volodymyr Kuleshov, Stefano Ermon
10. Improving Variational Inference with Inverse Autoregressive Flow
    Diederik P. Kingma, Tim Salimans, Max Welling
11. Learning Genomic Representations to Predict Clinical Outcomes in Cancer
    Safoora Yousefi, Congzheng Song, Nelson Nauata, Lee Cooper
12. Understanding Very Deep Networks via Volume Conservation
    Thomas Unterthiner, Sepp Hochreiter
13. Fixed Point Quantization of Deep Convolutional Networks
    Darryl D. Lin, Sachin S. Talathi, V. Sreekanth Annapureddy
14. CMA-ES for Hyperparameter Optimization of Deep Neural Networks
    Ilya Loshchilov, Frank Hutter
15. Understanding Visual Concepts with Continuation Learning
    William F. Whitney, Michael Chang, Tejas Kulkarni, Joshua B. Tenenbaum
16. Input-Convex Deep Networks
    Brandon Amos, J. Zico Kolter (moved to May 3rd)
17. Learning to SMILE(S)
    Stanisł‚aw Jastrzębski, Damian Leśniak, Wojciech Marian Czarnecki
18. Learning Retinal Tiling in a Model of Visual Attention
    Brian Cheung, Eric Weiss, Bruno Olshausen
19. Hardware-Friendly Convolutional Neural Network with Even-Number Filter Size
    Song Yao, Song Han, Kaiyuan Guo, Jianqiao Wangni, Yu Wang
20. Do Deep Convolutional Nets Really Need to be Deep (Or Even Convolutional)?
    Gregor Urban, Krzysztof J. Geras, Samira Ebrahimi Kahou, Ozlem Aslan Shengjie Wang, Rich Caruana, Abdelrahman Mohamed, Matthai Philipose, Matt Richardson
21. Generative Adversarial Metric
    Daniel Jiwoong Im, Chris Dongjoo Kim, Hui Jiang, Roland Memisevic
22. Revise Saturated Activation Functions
    Bing Xu, Ruitong Huang, Mu Li
23. Multi-layer Representation Learning for Medical Concepts
    Edward Choi, Mohammad Taha Bahadori, Jimeng Sun, Elizabeth Searles, Catherine Coffey
24. Alternative structures for character-level RNNs
    Piotr Bojanowski, Armand Joulin, Tomas Mikolov
25. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
    Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke
26. Revisiting Distributed Synchronous SGD
    Jianmin Chen, Rajat Monga, Samy Bengio, Rafal Jozefowicz
27. A Differentiable Transition Between Additive and Multiplicative Neurons
    Wiebke Koepp, Patrick van der Smagt, Sebastian Urban
28. Deep Autoresolution Networks
    Gabriel Pereyra, Christian Szegedy
29. Unsupervised Learning with Imbalanced Data via Structure Consolidation Latent Variable Model
    Fariba Yousefi, Zhenwen Dai, Carl Henrik Ek, Neil Lawrence
30. Robust Convolutional Neural Networks under Adversarial Noise
    Jonghoon Jin, Aysegul Dundar, Eugenio Culurciello
31. GradNets: Dynamic Interpolation Between Neural Architectures
    Diogo Almeida, Nate Sauder
32. Resnet in Resnet: Generalizing Residual Architectures
    Sasha Targ, Diogo Almeida, Kevin Lyman
33. Doctor AI: Predicting Clinical Events via Recurrent Neural Networks
    Edward Choi, Mohammad Taha Bahadori, Andy Schuetz, Walter F. Stewart, Joshua C. Denny, Bradley A. Malin, Jimeng Sun
34. On-the-fly Network Pruning for Object Detection
    Marc Masana, Joost van de Weijer, Andrew D. Bagdanov
35. Deep Directed Generative Models with Energy-Based Probability Estimation
    Taesup Kim, Yoshua Bengio
36. Rectified Factor Networks for Biclustering
    Djork-Arné Clevert, Thomas Unterthiner, Sepp Hochreiter
37. RandomOut: Using a convolutional gradient norm to win The Filter Lottery
    Joseph Paul Cohen, Henry Z. Lo, Wei Ding
38. Persistent RNNs: Stashing Weights on Chip
    Greg Diamos, Shubho Sengupta, Bryan Catanzaro, Mike Chrzanowski, Adam Coates, Erich Elsen, Jesse Engel, Awni Hannun, Sanjeev Satheesh
39. Scale Normalization
    Henry Z Lo, Kevin Amaral, Wei Ding
40. Close-to-clean regularization relates virtual adversarial training, ladder networks and others
    Mudassar Abbas, Jyri Kivinen, Tapani Raiko
41. Guided Sequence-to-Sequence Learning with External Rule Memory
    Jiatao Gu, Baotian Hu, Zhengdong Lu, Hang Li, Victor O.K. Li
42. Neural Text Understanding with Attention Sum Reader
    Rudolf Kadlec, Martin Schmid, Ondř™ej Bajgar, Jan Kleindienst
43. Incorporating Nesterov Momentum into Adam
    Timothy Dozat
44. Variational Inference for On-line Anomaly Detection in High-Dimensional Time Series
    Maximilian Sölch, Justin Bayer, Marvin Ludersdorfer, Patrick van der Smagt
45. Sequence-to-Sequence RNNs for Text Summarization
    Ramesh Nallapati, Bing Xiang, Bowen Zhou
46. Neural Generative Question Answering
    Jun Yin, Xin Jiang, Zhengdong Lu, Lifeng Shang, Hang Li, Xiaoming Li
47. Learning Document Embeddings by Predicting N-grams for Sentiment Classification of Long Movie Reviews
    Bofang Li, Tao Liu, Xiaoyong Du, Deyuan Zhang, Zhe Zhao
48. Autoencoding for Joint Relation Factorization and Discovery from Text
    Diego Marcheggiani, Ivan Titov
49. Adaptive Natural Gradient Learning Based on Riemannian Metric of Score Matching
    Ryo Karakida, Masato Okada, Shun-ichi Amari
50. Neural Enquirer: Learning to Query Tables in Natural Language
    Pengcheng Yin, Zhengdong Lu, Hang Li, Ben Kao
51. End to end speech recognition in English and Mandarin
    Dario Amodei, Rishita Anubhai, Eric Battenberg, Carl Case, Jared Casper, Bryan Catanzaro, Jingdong Chen, Mike Chrzanowski, Adam Coates, Greg Diamos, Erich Elsen, Jesse Engel, Linxi Fan, Christopher Fougner, Tony Han, Awni Hannun, Billy Jun, Patrick LeGresley, Libby Lin, Sharan Narang, Andrew Ng, Sherjil Ozair, Ryan Prenger, Jonathan Raiman, Sanjeev Satheesh, David Seetapun, Shubho Sengupta, Yi Wang, Zhiqian Wang, Chong Wang, Bo Xiao, Dani Yogatama, Jun Zhan, Zhenyao Zhu
52. Lessons from the Rademacher Complexity for Deep Learning
    Jure Sokolic, Raja Giryes, Guillermo Sapiro, Miguel R. D. Rodrigues
53. Coverage-based Neural Machine Translation
    Zhaopeng Tu, Zhengdong Lu, Yang Liu, Xiaohua Liu, Hang Li
54. Feed-Forward Networks with Attention Can Solve Some Long-Term Memory Problems
    Colin Raffel, Daniel P. W. Ellis
55. Learning stable representations in a changing world with on-line t-SNE: proof of concept in the songbird
    Stéphane Deny, Emily Mackevicius, Tatsuo Okubo, Gordon Berman, Joshua Shaevitz, Michale Fee

1. Mixtures of Sparse Autoregressive Networks
   Marc Goessling, Yali Amit
2. Comparative Study of Caffe, Neon, Theano, and Torch for Deep Learning
   Soheil Bahrampour, Naveen Ramakrishnan, Lukas Schott, Mohak Shah
3. Action Recognition using Visual Attention
   Shikhar Sharma, Ryan Kiros, Ruslan Salakhutdinov
4. Improving performance of recurrent neural network with relu nonlinearity
   Sachin S. Talathi, Aniket Vartak
5. Visualizing and Understanding Recurrent Networks
   Andrej Karpathy, Justin Johnson, Li Fei-Fei
6. Learning to Decompose for Object Detection and Instance Segmentation
   Eunbyung Park, Alexander C. Berg
7. Learning visual groups from co-occurrences in space and time
   Phillip Isola, Daniel Zoran, Dilip Krishnan, Edward H. Adelson
8. Spatio-Temporal Video Autoencoder with Differentiable Memory
   Viorica Patraucean, Ankur Handa, Roberto Cipolla
9. Task Loss Estimation for Structured Prediction
   Dzmitry Bahdanau, Dmiriy Serdyuk, Philémon Brakel, Nan Rosemary Ke, Jan Chorowski, Aaron Courville, Yoshua Bengio
10. Conditional computation in neural networks for faster models
    Emmanuel Bengio, Pierre-Luc Bacon, Joelle Pineau, Doina Precup
11. A metric learning approach for graph-based label propagation
    Pauline Wauquier, Mikaela Keller
12. Bidirectional Helmholtz Machines
    Jorg Bornschein, Samira Shabanian, Asja Fischer, Yoshua Bengio
13. A Controller-Recognizer Framework: How Necessary is Recogntion for Control?
    Marcin Moczulski, Kelvin Xu, Aaron Courville, Kyunghyun Cho
14. Online Batch Selection for Faster Training of Neural Networks
    Ilya Loshchilov, Frank Hutter
15. Nonparametric Canonical Correlation Analysis
    Tomer Michaeli, Weiran Wang, Karen Livescu
16. Document Context Language Models
    Yangfeng Ji, Trevor Cohn, Lingpeng Kong, Chris Dyer, Jacob Eisenstein
17. Unsupervised Learning of Visual Structure using Predictive Generative Networks
    William Lotter, Gabriel Kreiman, David Cox
18. Convolutional Clustering for Unsupervised Learning
    Aysegul Dundar, Jonghoon Jin, and Eugenio Culurciello
19. ParseNet: Looking Wider to See Better
    Wei Liu, Andrew Rabinovich, Alexander C. Berg
20. Why are deep nets reversible: A simple theory, with implications for training
    Sanjeev Arora, Yingyu Liang, Tengyu Ma
21. Binding via Reconstruction Clustering
    Klaus Greff, Rupesh Srivastava, Jürgen Schmidhuber
22. Dynamic Capacity Networks
    Amjad Almahairi, Nicolas Ballas, Tim Cooijmans, Yin Zheng, Hugo Larochelle, Aaron Courville
23. Learning Representations of Affect from Speech
    Sayan Ghosh, Eugene Laksana, Louis-Philippe Morency, Stefan Scherer
24. Neural Variational Inference for Text Processing
    Yishu Miao, Lei Yu, Phil Blunsom
25. Recurrent Models for Auditory Attention in Multi-Microphone Distance Speech Recognition
    Suyoun Kim, Ian Lane
26. A Deep Memory-based Architecture for Sequence-to-Sequence Learning
    Fandong Meng, Zhengdong Lu, Zhaopeng Tu, Hang Li, Qun Liu
27. Deconstructing the Ladder Network Architecture
    Mohammad Pezeshki, Linxi Fan, Philemon Brakel, Aaron Courville, Yoshua Bengio
28. Neural network-based clustering using pairwise constraints
    Yen-Chang Hsu, Zsolt Kira
29. LSTM-based Deep Learning Models for non-factoid answer selection
    Ming Tan, Cicero dos Santos, Bing Xiang, Bowen Zhou
30. Using Deep Learning to Predict Demographics from Mobile Phone Metadata
    Bjarke Felbo, Pål Sundsøy, Alex 'Sandy' Pentland, Sune Lehmann, Yves-Alexandre de Montjoye
31. Efficient Inference in Occlusion-Aware Generative Models of Images
    Jonathan Huang, Kevin Murphy
32. Convolutional Models for Joint Object Categorization and Pose Estimation
    Mohamed Elhoseiny, Tarek El-Gaaly, Amr Bakry, Ahmed Elgammal
33. Basic Level Categorization Facilitates Visual Object Recognition
    Panqu Wang, Garrison Cottrell
34. Learning to Represent Words in Context with Multilingual Supervision
    Kazuya Kawakami, Chris Dyer
35. Fine-grained pose prediction, normalization, and recognition
    Ning Zhang, Evan Shelhamer, Yang Gao, Trevor Darrell
36. Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters
    Jelena Luketina, Mathias Berglund, Tapani Raiko
37. Unitary Evolution Recurrent Neural Networks
    Martin Arjovsky, Amar Shah, Yoshua Bengio
38. Temporal Convolutional Neural Networks for Diagnosis from Lab Tests
    Narges Razavian, David Sontag
39. PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions
    Michael Figurnov, Dmitry Vetrov, Pushmeet Kohli
40. How far can we go without convolution: Improving fully-connected networks
    Zhouhan Lin, Roland Memisevic, Kishore Konda
41. Learning Dense Convolutional Embeddings for Semantic Segmentation
    Adam W. Harley, Konstantinos G. Derpanis, Iasonas Kokkinos
42. Generating Sentences from a Continuous Space
    Samuel R. Bowman, Luke Vilnis, Oriol Vinyals, Andrew M. Dai, Rafal Jozefowicz, Samy Bengio
43. Stacked What-Where Auto-encoders
    Junbo Zhao, Michael Mathieu, Ross Goroshin, Yann LeCun
44. Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
    Yarin Gal, Zoubin Ghahramani
45. Blending LSTMs into CNNs
    Krzysztof J. Geras, Abdel-rahman Mohamed, Rich Caruana, Gregor Urban, Shengjie Wang, Ozlem Aslan, Matthai Philipose, Matthew Richardson, Charles Sutton
46. Empirical performance upper bounds for image and video captioning
    Li Yao, Nicolas Ballas, Kyunghyun Cho, John R. Smith, Yoshua Bengio
47. Adversarial Autoencoders
    Alireza Makhzani, Jonathon Shlens, Navdeep Jaitly, Ian Goodfellow
48. Deep Reinforcement Learning with an Action Space Defined by Natural Language
    Ji He, Jianshu Chen, Xiaodong He, Jianfeng Gao, Lihong Li, Li Deng, Mari Ostendorf
49. Universum Prescription: Regularization using Unlabeled Data
    Xiang Zhang, Yann LeCun
50. Variance Reduction in SGD by Distributed Importance Sampling
    Guillaume Alain, Alex Lamb, Chinnadhurai Sankar, Aaron Courville, Yoshua Bengio
51. Adding Gradient Noise Improves Learning for Very Deep Networks
    Arvind Neelakantan, Luke Vilnis, Quoc V. Le, Ilya Sutskever, Lukasz Kaiser, Karol Kurach, James Martens
52. Black Box Variational Inference for State Space Models
    Evan Archer, Il Memming Park, Lars Buesing, John Cunningham, Liam Paninski
53. Input-Convex Deep Networks
    Brandon Amos, J. Zico Kolter

1. Multi-Scale Context Aggregation by Dilated Convolutions
   Fisher Yu, Vladlen Koltun
2. The Variational Fair Autoencoder
   Christos Louizos, Kevin Swersky, Yujia Li, Max Welling, Richard Zemel
3. A note on the evaluation of generative models
   Lucas Theis, Aäron van den Oord, Matthias Bethge
4. Learning to Diagnose with LSTM Recurrent Neural Networks
   Zachary Lipton, David Kale, Charles Elkan, Randall Wetzel
5. Prioritized Experience Replay
   Tom Schaul, John Quan, Ioannis Antonoglou, David Silver
6. Importance Weighted Autoencoders
   Yuri Burda, Ruslan Salakhutdinov, Roger Grosse
7. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
   Song Han, Huizi Mao, Bill Dally
8. Variationally Auto-Encoded Deep Gaussian Processes
   Zhenwen Dai, Andreas Damianou, Javier Gonzalez, Neil Lawrence
9. Training Convolutional Neural Networks with Low-rank Filters for Efficient Image Classification
   Yani Ioannou, Duncan Robertson, Jamie Shotton, roberto Cipolla, Antonio Criminisi, Jamie Shotton
10. Neural Networks with Few Multiplications
    Zhouhan Lin, Matthieu Courbariaux, Roland Memisevic, Yoshua Bengio
11. Reducing Overfitting in Deep Networks by Decorrelating Representations
    Michael Cogswell, Faruk Ahmed, Ross Girshick, Larry Zitnick, Dhruv Batra
12. Pushing the Boundaries of Boundary Detection using Deep Learning
    Iasonas Kokkinos
13. Generating Images from Captions with Attention
    Elman Mansimov, Emilio Parisotto, Jimmy Ba, Ruslan Salakhutdinov
14. Reasoning about Entailment with Neural Attention
    Tim Rocktäschel, Edward Grefenstette, Karl Moritz Hermann, Tomáš Kočiský, Phil Blunsom
15. Convolutional Neural Networks With Low-rank Regularization
    Cheng Tai, Tong Xiao, Yi Zhang, Xiaogang Wang, Weinan E
16. Unifying distillation and privileged information
    David Lopez-Paz, Leon Bottou, Bernhard Schölkopf, Vladimir Vapnik
17. Particular object retrieval with integral max-pooling of CNN activations [code]
    Giorgos Tolias, Ronan Sicre, Hervé Jégou
18. All you need is a good init [code]
    Dmytro Mishkin, Jiri Matas
19. Bayesian Representation Learning with Oracle Constraints
    Theofanis Karaletsos, Serge Belongie, Gunnar Rätsch
20. Neural Programmer: Inducing Latent Programs with Gradient Descent
    Arvind Neelakantan, Quoc Le, Ilya Sutskever
21. Towards Universal Paraphrastic Sentence Embeddings [code]
    John Wieting, Mohit Bansal, Kevin Gimpel, Karen Livescu
22. Regularizing RNNs by Stabilizing Activations
    David Krueger, Roland Memisevic
23. SparkNet: Training Deep Networks in Spark
    Philipp Moritz, Robert Nishihara, Ion Stoica, Michael Jordan
24. Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
    Jost Tobias Springenberg
25. The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
    Felix Hill, Antoine Bordes, Sumit Chopra, Jason Weston
26. MuProp: Unbiased Backpropagation For Stochastic Neural Networks
    Shixiang Gu, Sergey Levine, Ilya Sutskever, Andriy Mnih
27. Data Representation and Compression Using Linear-Programming Approximations
    Hristo Paskov, John Mitchell, Trevor Hastie
28. Diversity Networks
    Zelda Mariet, Suvrit Sra
29. Deep Reinforcement Learning in Parameterized Action Space [code] [data]
    Matthew Hausknecht, Peter Stone
30. Learning VIsual Predictive Models of Physics for Playing Billiards
    Katerina Fragkiadaki, Pulkit Agrawal, Sergey Levine, Jitendra Malik
31. Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks [code] [data]
    Jason Weston, Antoine Bordes, Sumit Chopra, Sasha Rush, Bart van Merrienboer, Armand Joulin, Tomas Mikolov
32. Evaluating Prerequisite Qualities for Learning End-to-end Dialog Systems [data]
    Jesse Dodge, Andreea Gane, Xiang Zhang, Antoine Bordes, Sumit Chopra, Alexander Miller, Arthur Szlam, Jason Weston
33. Better Computer Go Player with Neural Network and Long-term Prediction
    Yuandong Tian, Yan Zhu
34. Distributional Smoothing with Virtual Adversarial Training [code]
    Takeru Miyato, Shin-ichi Maeda, Masanori Koyama, Ken Nakae, Shin Ishii
35. Multi-task Sequence to Sequence Learning
    Minh-Thang Luong, Quoc Le, Ilya Sutskever, Oriol Vinyals, Lukasz Kaiser
36. A Test of Relative Similarity for Model Selection in Generative Models
    Eugene Belilovsky, Wacha Bounliphone, Matthew Blaschko, Ioannis Antonoglou, Arthur Gretton
37. Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications
    Yong-Deok Kim, Eunhyeok Park, Sungjoo Yoo, Taelim Choi, Lu Yang, Dongjun Shin
38. Neural Programmer-Interpreters
    Scott Reed, Nando de Freitas
39. Session-based recommendations with recurrent neural networks [code]
    Balázs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, Domonkos Tikk
40. Continuous control with deep reinforcement learning
    Timothy Lillicrap, Jonathan Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, Daan Wierstra
41. Recurrent Gaussian Processes
    César Lincoln Mattos, Zhenwen Dai, Andreas Damianou, Jeremy Forth, Guilherme Barreto, Neil Lawrence
42. Modeling Visual Representations:Defining Properties and Deep Approximations
    Stefano Soatto, Alessandro Chiuso
43. Auxiliary Image Regularization for Deep CNNs with Noisy Labels
    Samaneh Azadi, Jiashi Feng, Stefanie Jegelka, Trevor Darrell
44. Convergent Learning: Do different neural networks learn the same representations?
    Yixuan Li, Jason Yosinski, Jeff Clune, Hod Lipson, John Hopcroft
45. Policy Distillation
    Andrei Rusu, Sergio Gomez, Caglar Gulcehre, Guillaume Desjardins, James Kirkpatrick, Razvan Pascanu, Volodymyr Mnih, Koray Kavukcuoglu, Raia Hadsell
46. Neural Random-Access Machines
    Karol Kurach, Marcin Andrychowicz, Ilya Sutskever
47. Gated Graph Sequence Neural Networks
    Yujia Li, Daniel Tarlow, Marc Brockschmidt, Richard Zemel, CIFAR
48. Metric Learning with Adaptive Density Discrimination
    Oren Rippel, Manohar Paluri, Piotr Dollar, Lubomir Bourdev
49. Censoring Representations with an Adversary
    Harrison Edwards, Amos Storkey
50. Order-Embeddings of Images and Language [code]
    Ivan Vendrov, Ryan Kiros, Sanja Fidler, Raquel Urtasun
51. Variable Rate Image Compression with Recurrent Neural Networks
    George Toderici, Sean O'Malley, Damien Vincent, Sung Jin Hwang, Michele Covell, Shumeet Baluja, Rahul Sukthankar, David Minnen
52. Delving Deeper into Convolutional Networks for Learning Video Representations
    Nicolas Ballas, Li Yao, Pal Chris, Aaron Courville
53. 8-Bit Approximations for Parallelism in Deep Learning
    Tim Dettmers
54. Data-dependent initializations of Convolutional Neural Networks [code]
    Philipp Kraehenbuehl, Carl Doersch, Jeff Donahue, Trevor Darrell
55. Order Matters: Sequence to sequence for sets
    Oriol Vinyals, Samy Bengio, Manjunath Kudlur
56. High-Dimensional Continuous Control Using Generalized Advantage Estimation
    John Schulman, Philipp Moritz, Sergey Levine, Michael Jordan, Pieter Abbeel
57. BlackOut: Speeding up Recurrent Neural Network Language Models With Very Large Vocabularies [code]
    Shihao Ji, Swaminathan Vishwanathan, Nadathur Satish, Michael Anderson, Pradeep Dubey
58. Deep Multi Scale Video Prediction Beyond Mean Square Error
    Michael Mathieu, camille couprie, Yann Lecun
59. Grid Long Short-Term Memory
    Nal Kalchbrenner, Alex Graves, Ivo Danihelka
60. Net2Net: Accelerating Learning via Knowledge Transfer
    Tianqi Chen, Ian Goodfellow, Jon Shlens
61. Predicting distributions with Linearizing Belief Networks
    Yann Dauphin, David Grangier
62. Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
    Djork-Arné Clevert, Thomas Unterthiner, Sepp Hochreiter
63. Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
    Emilio Parisotto, Jimmy Ba, Ruslan Salakhutdinov
64. Segmental Recurrent Neural Networks
    Lingpeng Kong, Chris Dyer, Noah Smith
65. Deep Linear Discriminant Analysis [code]
    Matthias Dorfer, Rainer Kelz, Gerhard Widmer
66. Large-Scale Approximate Kernel Canonical Correlation Analysis
    Weiran Wang, Karen Livescu
67. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
    Alec Radford, Luke Metz, Soumith Chintala
68. Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks [code]
    Pouya Bashivan, Irina Rish, Mohammed Yeasin, Noel Codella
69. Digging Deep into the layers of CNNs: In Search of How CNNs Achieve View Invariance
    Amr Bakry, Mohamed Elhoseiny, Tarek El-Gaaly, Ahmed Elgammal
70. An Exploration of Softmax Alternatives Belonging to the Spherical Loss Family
    Alexandre De Brébisson, Pascal Vincent
71. Data-Dependent Path Normalization in Neural Networks
    Behnam Neyshabur, Ryota Tomioka, Ruslan Salakhutdinov, Nathan Srebro
72. Reasoning in Vector Space: An Exploratory Study of Question Answering
    Moontae Lee, Xiaodong He, Wen-tau Yih, Jianfeng Gao, Li Deng, Paul Smolensky
73. Neural GPUs Learn Algorithms [code] [video]
    Lukasz Kaiser, Ilya Sutskever
74. ACDC: A Structured Efficient Linear Layer
    Marcin Moczulski, Misha Denil, Jeremy Appleyard, Nando de Freitas
75. Density Modeling of Images using a Generalized Normalization Transformation
    Johannes Ballé, Valero Laparra, Eero Simoncelli
76. Adversarial Manipulation of Deep Representations [code]
    Sara Sabour, Yanshuai Cao, Fartash Faghri, David Fleet
77. Geodesics of learned representations
    Olivier Hénaff, Eero Simoncelli
78. Sequence Level Training with Recurrent Neural Networks
    Marc'Aurelio Ranzato, Sumit Chopra, Michael Auli, Wojciech Zaremba
79. Super-resolution with deep convolutional sufficient statistics
    Joan Bruna, Pablo Sprechmann, Yann Lecun
80. Variational Gaussian Process
    Dustin Tran, Rajesh Ranganath, David Blei

Talks should be no longer than 17 minutes, leaving 2-3 minutes for questions by the audience. The author who will be giving the talk must find the oral session chair in advance, to test the use of his/her personal laptop for presenting the slides.

Talks scheduled before the morning coffee break should do a laptop test before the morning session starts, while other talks can perform their tests during the coffee break.

The poster boards are 4 ft. high by 8 ft. wide. Poster presenters are encouraged to put up their posters as early as the day's morning coffee break (10:20 to 10:50).

Each poster is assigned a number, shown above. Presenters should use the poster board corresponding to the number for their work.

Once the poster session is over, presenters have until the end of the day to take off their posters from their assigned poster boards.