Universal Approximation with Certified Networks
Comments ICLR 2020
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
On the Weaknesses of Reinforcement Learning for Neural Machine Translation
Comments Accepted to ICLR 2020 (matching content, different style)
Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)
Comments 23 pages, 15 figures, ICLR 2020
Dynamics-aware Embeddings
Comments Published at ICLR 2020
Relational State-Space Model for Stochastic Multi-Object Systems
Comments Accepted by ICLR 2020
Towards GAN Benchmarks Which Require Generalization
Comments ICLR 2019 conference paper
A Closer Look at Few-shot Classification
Comments ICLR 2019. Code: https://github.com/wyharveychen/CloserLookFewShot . Project: https://sites.google.com/view/a-closer-look-at-few-shot/
Reanalysis of Variance Reduced Temporal Difference Learning
Comments To appear in ICLR 2020
Combining Q-Learning and Search with Amortized Value Estimates
Comments Published as a conference paper at ICLR 2020
On the Relationship between Self-Attention and Convolutional Layers
Comments To appear at ICLR 2020
Population-Guided Parallel Policy Search for Reinforcement Learning
Comments Accepted to ICLR 2020
Identity Crisis: Memorization and Generalization under Extreme Overparameterization
Comments ICLR 2020
Variational Hetero-Encoder Randomized GANs for Joint Image-Text Modeling
Comments ICLR 2020
Phase Transitions for the Information Bottleneck in Representation Learning
Comments ICLR 2020; 27 pages, 7 figures
Contrastive Learning of Structured World Models
Comments ICLR 2020
Automated Relational Meta-learning
Comments Accepted by ICLR 2020
Adversarial Lipschitz Regularization
Comments ICLR 2020
Working women and caste in India: A study of social disadvantage using feature attribution
Comments Presented at the ICLR AI for Social Good Workshop 2019; Updated with Addendum (Jan 2020)
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
Comments Published as a conference paper at ICLR 2020
Understanding Architectures Learnt by Cell-based Neural Architecture Search
Comments Published as a conference paper at ICLR 2020
Composing Task-Agnostic Policies with Deep Reinforcement Learning
Comments ICLR 2020
Synthetic Datasets for Neural Program Synthesis
Comments ICLR 2019
Observational Overfitting in Reinforcement Learning
Comments Published as a conference paper in ICLR 2020
The Implicit Bias of Depth: How Incremental Learning Drives Generalization
Comments 25 pages, 7 figures, published at the International Conference on Learning Representations (ICLR) 2020
Locality and compositionality in zero-shot learning
Comments Published at ICLR 2020
Influence-Based Multi-Agent Exploration
Journal ref International Conference on Learning Representations, 2020, spotlight
Variational Recurrent Models for Solving Partially Observable Control Tasks
Comments Published as a conference paper at the Eighth International Conference on Learning Representations (ICLR 2020)
Spectral embedding of regularized block models
Journal ref ICLR, 2020, Addis Abeba, Ethiopia
Diverse Trajectory Forecasting with Determinantal Point Processes
Comments ICLR 2020
Intriguing properties of adversarial training at scale
Comments To appear in ICLR 2020
