ICLR

Combining Learned Representations for Combinatorial Optimization

Saavan Patel, Sayeef Salahuddin

Comments Submitted to ICLR 2019

Robustness May Be at Odds with Accuracy

Dimitris Tsipras, Shibani Santurkar, Logan Engstrom, Alexander Turner, Aleksander Madry

Comments ICLR'19

Towards Deep Learning Models Resistant to Adversarial Attacks

Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu

Comments ICLR'18

Learning Multi-Level Hierarchies with Hindsight

Andrew Levy, George Konidaris, Robert Platt, Kate Saenko

Comments ICLR 2019 Accepted Paper

Spreading vectors for similarity search

Alexandre Sablayrolles, Matthijs Douze, Cordelia Schmid, Hervé Jégou

Comments Published at ICLR 2019

NOODL: Provable Online Dictionary Learning and Sparse Coding

Sirisha Rambhatla, Xingguo Li, Jarvis Haupt

Comments Published as a conference paper at the International Conference on Learning Representations (ICLR) 2019; 42 Pages with appendix

Modeling Uncertainty with Hedged Instance Embedding

Seong Joon Oh, Kevin Murphy, Jiyan Pan, Joseph Roth, Florian Schroff, Andrew Gallagher

Comments 15 pages, 11 figures, updated version of ICLR'19

Phrase-Based Attentions

Phi Xuan Nguyen, Shafiq Joty

Comments Under review as a conference paper at ICLR 2019

SHREWD: Semantic Hierarchy-based Relational Embeddings for Weakly-supervised Deep Hashing

Heikki Arponen, Tom E Bishop

Comments 4 pages, Published in ICLR LLD Workshop

Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment

Werner Zellinger, Bernhard A. Moser, Thomas Grubinger, Edwin Lughofer, Thomas Natschläger, Susanne Saminger-Platz

Comments Preliminary version of this work appeared in ICLR

Journal ref Information Sciences 483: 174-191, May 2019

Learning to Infer and Execute 3D Shape Programs

Yonglong Tian, Andrew Luo, Xingyuan Sun, Kevin Ellis, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu

Comments ICLR 2019. Project page: http://shape2prog.csail.mit.edu

Episodic Curiosity through Reachability

Nikolay Savinov, Anton Raichuk, Raphaël Marinier, Damien Vincent, Marc Pollefeys, Timothy Lillicrap, Sylvain Gelly

Comments Accepted to ICLR 2019. Code at https://github.com/google-research/episodic-curiosity/. Videos at https://sites.google.com/view/episodic-curiosity/

Representation Degeneration Problem in Training Natural Language Generation Models

Jun Gao, Di He, Xu Tan, Tao Qin, Liwei Wang, Tie-Yan Liu

Comments ICLR 2019

Environment Probing Interaction Policies

Wenxuan Zhou, Lerrel Pinto, Abhinav Gupta

Comments Published as a conference paper at ICLR 2019

Meta-learning with differentiable closed-form solvers

Luca Bertinetto, João F. Henriques, Philip H. S. Torr, Andrea Vedaldi

Comments Published at ICLR'19. Code and data available at http://www.robots.ox.ac.uk/~luca/r2d2.html

Delegative Reinforcement Learning: learning to avoid traps with a little help

Vanessa Kosoy

Comments 22 pages

Journal ref SafeML ICLR 2019 Workshop

Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning

Michael Lutter, Christian Ritter, Jan Peters

Comments Published at ICLR 2019

Active Learning with Partial Feedback

Peiyun Hu, Zachary C. Lipton, Anima Anandkumar, Deva Ramanan

Comments ICLR 2019

Towards Robust, Locally Linear Deep Networks

Guang-He Lee, David Alvarez-Melis, Tommi S. Jaakkola

Comments Published in International Conference on Learning Representations (ICLR), 2019

AI-based evaluation of the SDGs: The case of crop detection with earth observation data

Natalia Efremova, Dennis West, Dmitry Zausaev

Comments ICLR workshop "AI for Social Good"

Reproducibility in Machine Learning for Health

Matthew B. A. McDermott, Shirly Wang, Nikki Marinsek, Rajesh Ranganath, Marzyeh Ghassemi, Luca Foschini

Comments Presented at the ICLR 2019 Reproducibility in Machine Learning Workshop

GAN-based Generation and Automatic Selection of Explanations for Neural Networks

Saumitra Mishra, Daniel Stoller, Emmanouil Benetos, Bob L. Sturm, Simon Dixon

Comments 8 pages plus references and appendix. Accepted at the ICLR 2019 Workshop "Safe Machine Learning: Specification, Robustness and Assurance". Camera-ready version. v2: Corrected page header

Journal ref SafeML Workshop at the International Conference on Learning Representations (ICLR) 2019

Supervised Contextual Embeddings for Transfer Learning in Natural Language Processing Tasks

Mihir Kale, Aditya Siddhant, Sreyashi Nag, Radhika Parik, Matthias Grabmair, Anthony Tomasic

Comments Appeared in 2nd Learning from Limited Labeled Data (LLD) Workshop at ICLR 2019

Variational Autoencoder with Arbitrary Conditioning

Oleg Ivanov, Michael Figurnov, Dmitry Vetrov

Comments Published as a conference paper at ICLR 2019

Measuring and regularizing networks in function space

Ari S. Benjamin, David Rolnick, Konrad Kording

Comments Presented at ICLR 2019

Journal ref International Conference on Learning Representations, 2019, https://openreview.net/pdf?id=SkMwpiR9Y7

Hierarchical Policy Learning is Sensitive to Goal Space Design

Zach Dwiel, Madhavun Candadai, Mariano Phielipp, Arjun K. Bansal

Comments Accepted to be presented at Task-Agnostic Reinforcement Learning (TARL) workshop at ICLR'19

A Study of State Aliasing in Structured Prediction with RNNs

Layla El Asri, Adam Trischler

Comments Deep Reinforcement Learning Meets Structured Prediction workshop at ICLR 2019 and Representation Learning for NLP workshop at ACL 2019

Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics

Antonin Raffin, Ashley Hill, René Traoré, Timothée Lesort, Natalia Díaz-Rodríguez, David Filliat

Comments Github repo: https://github.com/araffin/srl-zoo Documentation: https://srl-zoo.readthedocs.io/en/latest/, As part of SRL-Toolbox: https://s-rl-toolbox.readthedocs.io/en/latest/. Accepted to the Workshop on Structure & Priors in Reinforcement Learning at ICLR 2019

AdaShift: Decorrelation and Convergence of Adaptive Learning Rate Methods

Zhiming Zhou, Qingru Zhang, Guansong Lu, Hongwei Wang, Weinan Zhang, Yong Yu

Comments Published as a conference paper at ICLR 2019

Neural Graph Evolution: Towards Efficient Automatic Robot Design

Tingwu Wang, Yuhao Zhou, Sanja Fidler, Jimmy Ba

Comments ICLR 2019