International Conference on Learning Representations (ICLR) - 2018

Conference Proceedings:

Key: PC - Pseudocode, OSC - Open Source Code, OSD - Open Datasets, DS - Dataset Splits, HS - Hardware Specification, SD - Software Dependencies, ES - Experiment Setup

A Bayesian Perspective on Generalization and Stochastic Gradient Descent 2
A Compressed Sensing View of Unsupervised Text Embeddings, Bag-of-n-Grams, and LSTMs 5
A DIRT-T Approach to Unsupervised Domain Adaptation 4
A Deep Reinforced Model for Abstractive Summarization 3
A Framework for the Quantitative Evaluation of Disentangled Representations 4
A Hierarchical Model for Device Placement 4
A Neural Representation of Sketch Drawings 4
A New Method of Region Embedding for Text Classification 5
A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks 0
A Scalable Laplace Approximation for Neural Networks 4
A Simple Neural Attentive Meta-Learner 4
Action-dependent Control Variates for Policy Optimization via Stein Identity 3
Activation Maximization Generative Adversarial Nets 3
Active Learning for Convolutional Neural Networks: A Core-Set Approach 5
Active Neural Localization 3
Adaptive Dropout with Rademacher Complexity Regularization 3
Adaptive Quantization of Neural Networks 4
Adversarial Dropout Regularization 3
All-but-the-Top: Simple and Effective Postprocessing for Word Representations 3
Alternating Multi-bit Quantization for Recurrent Neural Networks 5
AmbientGAN: Generative models from lossy measurements 3
An Online Learning Approach to Generative Adversarial Networks 4
An efficient framework for learning sentence representations 5
An image representation based convolutional network for DNA classification 4
Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy 3
Ask the Right Questions: Active Question Reformulation with Reinforcement Learning 3
Attacking Binarized Neural Networks 4
Auto-Conditioned Recurrent Networks for Extended Complex Human Motion Synthesis 3
Auto-Encoding Sequential Monte Carlo 2
Automatically Inferring Data Quality for Spatiotemporal Forecasting 2
Backpropagation through the Void: Optimizing control variates for black-box gradient estimation 4
Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer Ordering 3
Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs 4
Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling 6
Boosting Dilated Convolutional Networks with Mixed Tensor Decompositions 3
Boosting the Actor with Dual Critic 3
Boundary Seeking GANs 4
Breaking the Softmax Bottleneck: A High-Rank RNN Language Model 4
Can Neural Networks Understand Logical Entailment? 2
Can recurrent neural networks warp time? 3
Cascade Adversarial Machine Learning Regularized with a Unified Embedding 2
CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training 2
Certified Defenses against Adversarial Examples 3
Certifying Some Distributional Robustness with Principled Adversarial Training 3
Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality 4
Combining Symbolic Expressions and Black-box Function Evaluations in Neural Programs 3
Communication Algorithms via Deep Learning 2
Compositional Attention Networks for Machine Reasoning 4
Compositional Obverter Communication Learning from Raw Visual Input 2
Compressing Word Embeddings via Deep Compositional Code Learning 3
Consequentialist conditional cooperation in social dilemmas with imperfect information 2
Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments 2
Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields 4
Countering Adversarial Images using Input Transformations 3
Critical Percolation as a Framework to Analyze the Training of Deep Networks 2
Critical Points of Linear Neural Networks: Analytical Forms and Landscape Properties 0
DCN+: Mixed Objective And Deep Residual Coattention for Question Answering 3
DORA The Explorer: Directed Outreaching Reinforcement Action-Selection 4
Debiasing Evidence Approximations: On Importance-weighted Autoencoders and Jackknife Variational Inference 6
Decision Boundary Analysis of Adversarial Examples 4
Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models 6
Decoupling the Layers in Residual Networks 3
Deep Active Learning for Named Entity Recognition 5
Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection 2
Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling 4
Deep Complex Networks 5
Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking 5
Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training 5
Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design 2
Deep Learning as a Mixed Convex-Combinatorial Optimization Problem 6
Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge 4
Deep Learning with Logged Bandit Feedback 3
Deep Neural Networks as Gaussian Processes 4
Deep Rewiring: Training very sparse deep networks 6
Deep Sensing: Active Sensing using Multi-directional Recurrent Neural Networks 4
Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning 3
Deep contextualized word representations 3
Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models 4
Demystifying MMD GANs 4
Depthwise Separable Convolutions for Neural Machine Translation 3
Detecting Statistical Interactions from Neural Network Weights 4
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting 4
Distributed Distributional Deterministic Policy Gradients 3
Distributed Fine-tuning of Language Models on Private Data 3
Distributed Prioritized Experience Replay 4
Divide and Conquer Networks 3
Divide-and-Conquer Reinforcement Learning 2
Do GANs learn the distribution? Some Theory and Empirics 2
Don't Decay the Learning Rate, Increase the Batch Size 3
Dynamic Neural Program Embeddings for Program Repair 3
Efficient Sparse-Winograd Convolutional Neural Networks 2
Eigenoption Discovery through the Deep Successor Representation 3
Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input 3
Emergence of grid-like representations by training recurrent neural networks to perform spatial localization 1
Emergent Communication in a Multi-Modal, Multi-Step Referential Game 4
Emergent Communication through Negotiation 1
Emergent Complexity via Multi-Agent Competition 2
Emergent Translation in Multi-Agent Communication 3
Empirical Risk Landscape Analysis for Understanding Deep Neural Networks 0
Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks 4
Ensemble Adversarial Training: Attacks and Defenses 3
Espresso: Efficient Forward Propagation for Binary Deep Neural Networks 4
Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach 5
Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering 4
Expressive power of recurrent neural networks 2
FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling 6
FearNet: Brain-Inspired Model for Incremental Learning 3
Few-Shot Learning with Graph Neural Networks 3
Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions 4
Fidelity-Weighted Learning 4
Fix your classifier: the marginal value of training the last weight layer 4
Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches 3
Fraternal Dropout 4
FusionNet: Fusing via Fully-aware Attention with Application to Machine Comprehension 5
GANITE: Estimation of Individualized Treatment Effects using Generative Adversarial Nets 4
Gaussian Process Behaviour in Wide Deep Neural Networks 2
Generalizing Across Domains via Cross-Gradient Training 5
Generalizing Hamiltonian Monte Carlo with Neural Networks 4
Generating Natural Adversarial Examples 4
Generating Wikipedia by Summarizing Long Sequences 4
Generative Models of Visually Grounded Imagination 4
Generative networks as inverse problems with Scattering transforms 3
Global Optimality Conditions for Deep Neural Networks 0
Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning 4
Gradient Estimators for Implicit Models 5
Graph Attention Networks 4
Guide Actor-Critic for Continuous Control 4
HexaConv 2
Hierarchical Density Order Embeddings 5
Hierarchical Representations for Efficient Architecture Search 5
Hierarchical Subtask Discovery with Non-Negative Matrix Factorization 0
Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning 2
Hyperparameter optimization: a spectral approach 4
Identifying Analogies Across Domains 2
Imitation Learning from Visual Data with Multiple Intentions 3
Implicit Causal Models for Genome-wide Association Studies 2
Improving GAN Training via Binarized Representation Entropy (BRE) Regularization 2
Improving GANs Using Optimal Transport 3
Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect 5
Improving the Universality and Learnability of Neural Programmer-Interpreters with Combinator Abstraction 2
Initialization matters: Orthogonal Predictive State Recurrent Neural Networks 3
Interactive Grounded Language Acquisition and Generalization in a 2D World 2
Interpretable Counting for Visual Question Answering 3
Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play 4
Kernel Implicit Variational Inference 4
Kronecker-factored Curvature Approximations for Recurrent Neural Networks 5
LEARNING TO SHARE: SIMULTANEOUS PARAMETER TYING AND SPARSIFICATION IN DEEP LEARNING 3
Large Scale Optimal Transport and Mapping Estimation 3
Large scale distributed neural network training through online distillation 4
Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models 2
Latent Space Oddity: on the Curvature of Deep Generative Models 4
Learn to Pay Attention 4
Learning Approximate Inference Networks for Structured Prediction 3
Learning Awareness Models 2
Learning Deep Mean Field Games for Modeling Large Population Behavior 2
Learning Differentially Private Recurrent Language Models 3
Learning Discrete Weights Using the Local Reparameterization Trick 4
Learning From Noisy Singly-labeled Data 4
Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning 5
Learning Intrinsic Sparse Structures within Long Short-Term Memory 6
Learning Latent Permutations with Gumbel-Sinkhorn Networks 4
Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization 4
Learning One-hidden-layer Neural Networks with Landscape Design 1
Learning Parametric Closed-Loop Policies for Markov Potential Games 1
Learning Robust Rewards with Adverserial Inverse Reinforcement Learning 4
Learning Sparse Latent Representations with the Deep Copula Information Bottleneck 2
Learning Sparse Neural Networks through L_0 Regularization 2
Learning Wasserstein Embeddings 4
Learning a Generative Model for Validity in Complex Discrete Structures 2
Learning a neural response metric for retinal prosthesis 1
Learning an Embedding Space for Transferable Robot Skills 1
Learning from Between-class Examples for Deep Sound Recognition 5
Learning how to explain neural networks: PatternNet and PatternAttribution 5
Learning to Count Objects in Natural Images for Visual Question Answering 4
Learning to Multi-Task by Active Sampling 4
Learning to Represent Programs with Graphs 5
Learning to Teach 4
Learning to cluster in order to transfer across domains and tasks 3
Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning 3
Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis 3
Lifelong Learning with Dynamically Expandable Networks 4
Loss-aware Weight Quantization of Deep Networks 5
META LEARNING SHARED HIERARCHIES 2
MGAN: Training Generative Adversarial Nets with Multiple Generators 5
Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step 2
MaskGAN: Better Text Generation via Filling in the _______ 4
Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent 3
Matrix capsules with EM routing 3
Maximum a Posteriori Policy Optimisation 3
Measuring the Intrinsic Dimension of Objective Landscapes 2
Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks 4
Memory Architectures in Recurrent Neural Network Language Models 2
Memory Augmented Control Networks 1
Memory-based Parameter Adaptation 4
Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm 2
Meta-Learning for Semi-Supervised Few-Shot Classification 4
Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation 4
Minimax Curriculum Learning: Machine Teaching with Desirable Difficulties and Scheduled Diversity 3
Mitigating Adversarial Effects Through Randomization 3
Mixed Precision Training 4
Mixed Precision Training of Convolutional Neural Networks using Integer Operations 5
Model compression via distillation and quantization 5
Model-Ensemble Trust-Region Policy Optimization 5
Modular Continual Learning in a Unified Visual Environment 3
Monotonic Chunkwise Attention 5
Multi-Mention Learning for Reading Comprehension with Neural Cascades 4
Multi-Scale Dense Networks for Resource Efficient Image Classification 4
Multi-Task Learning for Document Ranking and Query Suggestion 5
Multi-View Data Generation Without View Supervision 3
Multi-level Residual Networks from Dynamical Systems View 3
N2N learning: Network to Network Compression via Policy Gradient Reinforcement Learning 5
Natural Language Inference over Interaction Space 4
NerveNet: Learning Structured Policy with Graph Neural Networks 3
Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks 4
Neural Language Modeling by Jointly Learning Syntax and Lexicon 3
Neural Map: Structured Memory for Deep Reinforcement Learning 2
Neural Sketch Learning for Conditional Program Generation 5
Neural Speed Reading via Skim-RNN 4
Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples 4
Noisy Networks For Exploration 3
Non-Autoregressive Neural Machine Translation 5
Not-So-Random Features 4
On Unifying Deep Generative Models 2
On the Convergence of Adam and Beyond 3
On the Discrimination-Generalization Tradeoff in GANs 1
On the Expressive Power of Overlapping Architectures of Deep Learning 3
On the Information Bottleneck Theory of Deep Learning 3
On the State of the Art of Evaluation in Neural Language Models 3
On the importance of single directions for generalization 2
On the insufficiency of existing momentum schemes for Stochastic Optimization 5
On the regularization of Wasserstein GANs 3
Online Learning Rate Adaptation with Hypergradient Descent 6
Overcoming Catastrophic Interference using Conceptor-Aided Backpropagation 3
Parallelizing Linear Recurrent Neural Nets Over Sequence Length 4
Parameter Space Noise for Exploration 3
Parametrized Hierarchical Procedures for Neural Programming 2
PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples 4
PixelNN: Example-based Image Synthesis 3
Polar Transformer Networks 4
Policy Optimization by Genetic Distillation 4
Predicting Floor-Level for 911 Calls with Neural Networks and Smartphone Sensor Data 5
Progressive Growing of GANs for Improved Quality, Stability, and Variation 4
Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control 1
Proximal Backpropagation 6
QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension 4
Quantitatively Evaluating GANs With Divergences Proposed for Training 4
Recasting Gradient-Based Meta-Learning as Hierarchical Bayes 5
Regularizing and Optimizing LSTM Language Models 5
Reinforcement Learning Algorithm Selection 3
Reinforcement Learning on Web Interfaces using Workflow-Guided Exploration 4
Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions 5
Residual Connections Encourage Iterative Inference 2
Residual Loss Prediction: Reinforcement Learning With No Incremental Feedback 5
Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers 3
Robustness of Classifiers to Universal Perturbations: A Geometric Perspective 3
Routing Networks: Adaptive Selection of Non-Linear Functions for Multi-Task Learning 3
SCAN: Learning Hierarchical Compositional Visual Concepts 3
SEARNN: Training RNNs with global-local losses 4
SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data 1
SMASH: One-Shot Model Architecture Search through HyperNetworks 5
Scalable Private Learning with PATE 3
Self-ensembling for visual domain adaptation 5
Semantic Interpolation in Implicit Models 2
Semantically Decomposing the Latent Spaces of Generative Adversarial Networks 5
Semi-parametric topological memory for navigation 3
Sensitivity and Generalization in Neural Networks: an Empirical Study 3
Simulated+Unsupervised Learning With Adaptive Data Generation and Bidirectional Mappings 2
Simulating Action Dynamics with Neural Process Networks 3
Skip Connections Eliminate Singularities 2
Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks 5
Smooth Loss Functions for Deep Top-k Classification 6
Sobolev GAN 4
Sparse Persistent RNNs: Squeezing Large Recurrent Networks On-Chip 6
Spatially Transformed Adversarial Examples 2
Spectral Normalization for Generative Adversarial Networks 4
SpectralNet: Spectral Clustering using Deep Neural Networks 6
Spherical CNNs 3
Stabilizing Adversarial Nets with Prediction Methods 6
Stochastic Activation Pruning for Robust Adversarial Defense 5
Stochastic Variational Video Prediction 2
Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks 2
Syntax-Directed Variational Autoencoder for Structured Data 5
Synthesizing realistic neural population activity patterns using Generative Adversarial Networks 3
Synthetic and Natural Noise Both Break Neural Machine Translation 4
TD or not TD: Analyzing the Role of Temporal Differencing in Deep Reinforcement Learning 2
TRAINING GENERATIVE ADVERSARIAL NETWORKS VIA PRIMAL-DUAL SUBGRADIENT METHODS: A LAGRANGIAN PERSPECTIVE ON GAN 3
TRUNCATED HORIZON POLICY SEARCH: COMBINING REINFORCEMENT LEARNING & IMITATION LEARNING 1
Temporal Difference Models: Model-Free Deep RL for Model-Based Control 2
Temporally Efficient Deep Learning with Spikes 3
The High-Dimensional Geometry of Binary Neural Networks 2
The Implicit Bias of Gradient Descent on Separable Data 4
The Kanerva Machine: A Generative Distributed Memory 4
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning 2
The Role of Minimal Complexity Functions in Unsupervised Learning of Semantic Mappings 3
The power of deeper networks for expressing natural functions 1
Thermometer Encoding: One Hot Way To Resist Adversarial Examples 3
Towards Deep Learning Models Resistant to Adversarial Attacks 3
Towards Image Understanding from Deep Compression Without Decoding 5
Towards Neural Phrase-based Machine Translation 5
Towards Reverse-Engineering Black-Box Neural Networks 5
Towards Synthesizing Complex Programs From Input-Output Examples 2
Towards better understanding of gradient-based attribution methods for Deep Neural Networks 3
Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples 5
Training GANs with Optimism 5
Training and Inference with Integers in Deep Neural Networks 5
Training wide residual networks for deployment using a single bit for each weight 4
TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning 3
Trust-PCL: An Off-Policy Trust Region Method for Continuous Control 4
Twin Networks: Matching the Future for Sequence Generation 4
Unbiased Online Recurrent Optimization 4
Understanding Deep Neural Networks with Rectified Linear Units 1
Understanding Short-Horizon Bias in Stochastic Meta-Optimization 4
Understanding image motion with group representations 2
Universal Agent for Disentangling Environments and Tasks 2
Unsupervised Cipher Cracking Using Discrete GANs 3
Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration 3
Unsupervised Machine Translation Using Monolingual Corpora Only 4
Unsupervised Neural Machine Translation 4
Unsupervised Representation Learning by Predicting Image Rotations 3
Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines 2
Variational Continual Learning 4
Variational Inference of Disentangled Latent Concepts from Unlabeled Observations 2
Variational Message Passing with Structured Inference Networks 5
Variational Network Quantization 2
Variational image compression with a scale hyperprior 1
Viterbi-based Pruning for Sparse Matrix with Fixed and High Index Compression Ratio 3
VoiceLoop: Voice Fitting and Synthesis via a Phonological Loop 5
WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling 3
WRPN: Wide Reduced-Precision Networks 3
Wasserstein Auto-Encoders 4
Wavelet Pooling for Convolutional Neural Networks 6
When is a Convolutional Filter Easy to Learn? 1
Word translation without parallel data 4
Zero-Shot Visual Imitation 2
cGANs with Projection Discriminator 5
i-RevNet: Deep Invertible Networks 4
mixup: Beyond Empirical Risk Minimization 6