ICLR 2017

This is an old revision of the document!


Conference Poster Sessions

Below are the Conference Track papers presented at each of the poster sessions (on Monday, Tuesday or Wednesday, in the morning or evening). To find a paper, look for the poster with the corresponding number in the area dedicated to the Conference Track.

Monday Morning (April 24th, 10:30am to 12:30pm)

  1. Making Neural Programming Architectures Generalize via Recursion
  2. Learning Graphical State Transitions
  3. Distributed Second-Order Optimization using Kronecker-Factored Approximations
  4. Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes
  5. Neural Program Lattices
  6. Diet Networks: Thin Parameters for Fat Genomics
  7. Unsupervised Cross-Domain Image Generation
  8. Towards Principled Methods for Training Generative Adversarial Networks
  9. Recurrent Mixture Density Network for Spatiotemporal Visual Attention
  10. Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
  11. Pruning Filters for Efficient ConvNets
  12. Optimization as a Model for Few-Shot Learning
  13. Understanding deep learning requires rethinking generalization
  14. On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
  15. Recurrent Hidden Semi-Markov Model
  16. Nonparametric Neural Networks
  17. Learning to Generate Samples from Noise through Infusion Training
  18. An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population Infomax
  19. Highway and Residual Networks learn Unrolled Iterative Estimation
  20. Soft Weight-Sharing for Neural Network Compression
  21. Snapshot Ensembles: Train 1, Get M for Free
  22. Towards a Neural Statistician
  23. Learning Curve Prediction with Bayesian Neural Networks
  24. Learning End-to-End Goal-Oriented Dialog
  25. Multi-Agent Cooperation and the Emergence of (Natural) Language
  26. Efficient Vector Representation for Documents through Corruption
  27. Improving Neural Language Models with a Continuous Cache
  28. Program Synthesis for Character Level Language Modeling
  29. Tracking the World State with Recurrent Entity Networks
  30. Reinforcement Learning with Unsupervised Auxiliary Tasks
  31. Neural Architecture Search with Reinforcement Learning
  32. Sample Efficient Actor-Critic with Experience Replay
  33. Learning to Act by Predicting the Future

Monday Afternoon (April 24th, 4:30pm to 6:30pm)

  1. Neuro-Symbolic Program Synthesis
  2. Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy
  3. Trained Ternary Quantization
  4. DSD: Dense-Sparse-Dense Training for Deep Neural Networks
  5. A Compositional Object-Based Approach to Learning Physical Dynamics
  6. Multilayer Recurrent Network Models of Primate Retinal Ganglion Cells
  7. Improving Generative Adversarial Networks with Denoising Feature Matching
  8. Transfer of View-manifold Learning to Similarity Perception of Novel Objects
  9. What does it take to generate natural textures?
  10. Emergence of foveal image sampling from learning to attend in visual scenes
  11. PixelCNN++: A PixelCNN Implementation with Discretized Logistic Mixture Likelihood and Other Modifications
  12. Learning to Optimize
  13. Training Compressed Fully-Connected Networks with a Density-Diversity Penalty
  14. Optimal Binary Autoencoding with Pairwise Correlations
  15. On the Quantitative Analysis of Decoder-Based Generative Models
  16. Learning to Remember Rare Events
  17. Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks
  18. Capacity and Learnability in Recurrent Neural Networks
  19. Deep Learning with Dynamic Computation Graphs
  20. Exploring Sparsity in Recurrent Neural Networks
  21. Structured Attention Networks
  22. Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
  23. Variational Lossy Autoencoder
  24. Learning to Query, Reason, and Answer Questions On Ambiguous Texts
  25. Deep Biaffine Attention for Neural Dependency Parsing
  26. A Compare-Aggregate Model for Matching Text Sequences
  27. Data Noising as Smoothing in Neural Network Language Models
  28. Neural Variational Inference For Topic Models
  29. Words or Characters? Fine-grained Gating for Reading Comprehension
  30. Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic
  31. Stochastic Neural Networks for Hierarchical Reinforcement Learning
  32. Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning
  33. Third Person Imitation Learning

Tuesday Morning (April 25th, 10:30am to 12:30pm)

  1. DeepDSL: A Compilation-based Domain-Specific Language for Deep Learning
  2. SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
  3. Deep Probabilistic Programming
  4. Lie-Access Neural Turing Machines
  5. Learning Features of Music From Scratch
  6. Mode Regularized Generative Adversarial Networks
  7. End-to-end Optimized Image Compression
  8. Variational Recurrent Adversarial Deep Domain Adaptation
  9. Steerable CNNs
  10. Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
  11. PixelVAE: A Latent Variable Model for Natural Images
  12. A recurrent neural network without chaos
  13. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
  14. Tree-structured decoding with doubly-recurrent neural networks
  15. Introspection:Accelerating Neural Network Training By Learning Weight Evolution
  16. Hyperband: Bandit-Based Configuration Evaluation for Hyperparameter Optimization
  17. Quasi-Recurrent Neural Networks
  18. Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain
  19. A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
  20. Trusting SVM for Piecewise Linear CNNs
  21. Maximum Entropy Flow Networks
  22. The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
  23. Unrolled Generative Adversarial Networks
  24. A Simple but Tough-to-Beat Baseline for Sentence Embeddings
  25. Query-Reduction Networks for Question Answering
  26. Machine Comprehension Using Match-LSTM and Answer Pointer
  27. Bidirectional Attention Flow for Machine Comprehension
  28. Dynamic Coattention Networks For Question Answering
  29. Multi-view Recurrent Neural Acoustic Word Embeddings
  30. Episodic Exploration for Deep Deterministic Policies for StarCraft Micromanagement
  31. Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning
  32. Generalizing Skills with Semi-Supervised Reinforcement Learning
  33. Improving Policy Gradient by Exploring Under-appreciated Rewards

Tuesday Afternoon (April 25th, 4:30pm to 6:30pm)

  1. Sigma Delta Quantized Networks
  2. Paleo: A Performance Model for Deep Neural Networks
  3. DeepCoder: Learning to Write Programs
  4. Topology and Geometry of Deep Rectified Network Optimization Landscapes
  5. Incremental Network Quantization: Towards Lossless CNNs with Low-precision Weights
  6. Learning to Perform Physics Experiments via Deep Reinforcement Learning
  7. Decomposing Motion and Content for Natural Video Sequence Prediction
  8. Calibrating Energy-based Generative Adversarial Networks
  9. Pruning Convolutional Neural Networks for Resource Efficient Inference
  10. Incorporating long-range consistency in CNN-based texture generation
  11. Lossy Image Compression with Compressive Autoencoders
  12. LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation
  13. Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data
  14. Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data
  15. Mollifying Networks
  16. beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
  17. Categorical Reparameterization with Gumbel-Softmax
  18. Online Bayesian Transfer Learning for Sequential Data Modeling
  19. Latent Sequence Decompositions
  20. Density estimation using Real NVP
  21. Recurrent Batch Normalization
  22. SGDR: Stochastic Gradient Descent with Restarts
  23. Variable Computation in Recurrent Neural Networks
  24. Deep Variational Information Bottleneck
  25. A SELF-ATTENTIVE SENTENCE EMBEDDING
  26. TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency
  27. Frustratingly Short Attention Spans in Neural Language Modeling
  28. Offline Bilingual Word Vectors Without a Dictionary
  29. LEARNING A NATURAL LANGUAGE INTERFACE WITH NEURAL PROGRAMMER
  30. Designing Neural Network Architectures using Reinforcement Learning
  31. Metacontrol for Adaptive Imagination-Based Optimization
  32. Recurrent Environment Simulators
  33. EPOpt: Learning Robust Neural Network Policies Using Model Ensembles

Wednesday Morning (April 26th, 10:30am to 12:30pm)

  1. Deep Multi-task Representation Learning: A Tensor Factorisation Approach
  2. Training deep neural-networks using a noise adaptation layer
  3. Delving into Transferable Adversarial Examples and Black-box Attacks
  4. Towards the Limit of Network Quantization
  5. Towards Deep Interpretability (MUS-ROVER II): Learning Hierarchical Representations of Tonal Music
  6. Learning to superoptimize programs
  7. Regularizing CNNs with Locally Constrained Decorrelations
  8. Generative Multi-Adversarial Networks
  9. Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
  10. FractalNet: Ultra-Deep Neural Networks without Residuals
  11. Faster CNNs with Direct Sparse Convolutions and Guided Pruning
  12. FILTER SHAPING FOR CONVOLUTIONAL NEURAL NETWORKS
  13. The Neural Noisy Channel
  14. Automatic Rule Extraction from Long Short Term Memory Networks
  15. Adversarially Learned Inference
  16. Deep Information Propagation
  17. Revisiting Classifier Two-Sample Tests
  18. Loss-aware Binarization of Deep Networks
  19. Energy-based Generative Adversarial Networks
  20. Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
  21. Temporal Ensembling for Semi-Supervised Learning
  22. On Detecting Adversarial Perturbations
  23. Identity Matters in Deep Learning
  24. Adversarial Feature Learning
  25. Learning through Dialogue Interactions
  26. Learning to Compose Words into Sentences with Reinforcement Learning
  27. Batch Policy Gradient Methods for Improving Neural Conversation Models
  28. Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling
  29. Geometry of Polysemy
  30. PGQ: Combining policy gradient and Q-learning
  31. Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU
  32. Learning to Navigate in Complex Environments
  33. Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks

Wednesday Afternoon (April 26th, 4:30pm to 6:30pm)

  1. Learning recurrent representations for hierarchical behavior modeling
  2. Predicting Medications from Diagnostic Codes with Recurrent Neural Networks
  3. Sparsely-Connected Neural Networks: Towards Efficient VLSI Implementation of Deep Neural Networks
  4. HolStep: A Machine Learning Dataset for Higher-order Logic Theorem Proving
  5. Learning Invariant Representations Of Planar Curves
  6. Entropy-SGD: Biasing Gradient Descent Into Wide Valleys
  7. Amortised MAP Inference for Image Super-resolution
  8. Inductive Bias of Deep Convolutional Networks through Pooling Geometry
  9. Neural Photo Editing with Introspective Adversarial Networks
  10. A Learned Representation For Artistic Style
  11. Adversarial Machine Learning at Scale
  12. Stick-Breaking Variational Autoencoders
  13. Support Regularized Sparse Coding and Its Fast Encoder
  14. Discrete Variational Autoencoders
  15. Do Deep Convolutional Nets Really Need to be Deep and Convolutional?
  16. Efficient Representation of Low-Dimensional Manifolds using Deep Networks
  17. Semi-Supervised Classification with Graph Convolutional Networks
  18. Understanding Neural Sparse Coding with Matrix Factorization
  19. Tighter bounds lead to improved classifiers
  20. Why Deep Neural Networks for Function Approximation?
  21. Hierarchical Multiscale Recurrent Neural Networks
  22. Dropout with Expectation-linear Regularization
  23. HyperNetworks
  24. Hadamard Product for Low-rank Bilinear Pooling
  25. Adversarial Training Methods for Semi-Supervised Text Classification
  26. Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
  27. Pointer Sentinel Mixture Models
  28. Reasoning with Memory Augmented Neural Networks for Language Comprehension
  29. Dialogue Learning With Human-in-the-Loop
  30. Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning
  31. Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening
  32. Learning Visual Servoing with Deep Features and Trust Region Fitted Q-Iteration
  33. An Actor-Critic Algorithm for Sequence Prediction