ICLR

Semantically-Guided Representation Learning for Self-Supervised Monocular Depth

Vitor Guizilini, Rui Hou, Jie Li, Rares Ambrus, Adrien Gaidon

Comments Proceedings of the Eighth International Conference on Learning Representations (ICLR 2020)

Optimistic Exploration even with a Pessimistic Initialisation

Tabish Rashid, Bei Peng, Wendelin Böhmer, Shimon Whiteson

Comments Published as a conference paper at ICLR 2020

State-only Imitation with Transition Dynamics Mismatch

Tanmay Gangwani, Jian Peng

Comments ICLR 2020 camera-ready

Rethinking the Hyperparameters for Fine-tuning

Hao Li, Pratik Chaudhari, Hao Yang, Michael Lam, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto

Comments Published as a conference paper at ICLR 2020

GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation

Chence Shi, Minkai Xu, Zhaocheng Zhu, Weinan Zhang, Ming Zhang, Jian Tang

Journal ref Published at ICLR 2020

A Latent Morphology Model for Open-Vocabulary Neural Machine Translation

Duygu Ataman, Wilker Aziz, Alexandra Birch

Comments Published at ICLR 2020

Revisiting Ensembles in an Adversarial Context: Improving Natural Accuracy

Aditya Saligrama, Guillaume Leclerc

Comments 5 pages, accepted to ICLR 2020 Workshop on Towards Trustworthy ML: Rethinking Security and Privacy for ML

Capsules with Inverted Dot-Product Attention Routing

Yao-Hung Hubert Tsai, Nitish Srivastava, Hanlin Goh, Ruslan Salakhutdinov

Comments ICLR 2020

Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP

Haonan Yu, Sergey Edunov, Yuandong Tian, Ari S. Morcos

Comments ICLR 2020

Network Deconvolution

Chengxi Ye, Matthew Evanusa, Hua He, Anton Mitrokhin, Tom Goldstein, James A. Yorke, Cornelia Fermüller, Yiannis Aloimonos

Comments ICLR 2020

Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based Optimization

Satrajit Chatterjee

Comments To appear in ICLR 2020

A Theory of Usable Information Under Computational Constraints

Yilun Xu, Shengjia Zhao, Jiaming Song, Russell Stewart, Stefano Ermon

Comments ICLR 2020 (Talk)

I Am Going MAD: Maximum Discrepancy Competition for Comparing Classifiers Adaptively

Haotao Wang, Tianlong Chen, Zhangyang Wang, Kede Ma

Comments Accepted to ICLR 2020

Differentiable Reasoning over a Virtual Knowledge Base

Bhuwan Dhingra, Manzil Zaheer, Vidhisha Balachandran, Graham Neubig, Ruslan Salakhutdinov, William W. Cohen

Comments ICLR 2020

Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference

Ting-Kuei Hu, Tianlong Chen, Haotao Wang, Zhangyang Wang

Comments Published on ICLR 2020

Are Transformers universal approximators of sequence-to-sequence functions?

Chulhee Yun, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar

Comments 23 pages, ICLR 2020 camera-ready version

Stochastic Conditional Generative Networks with Basis Decomposition

Ze Wang, Xiuyuan Cheng, Guillermo Sapiro, Qiang Qiu

Comments Published as a conference paper at ICLR 2020

The Early Phase of Neural Network Training

Jonathan Frankle, David J. Schwab, Ari S. Morcos

Comments ICLR 2020 Camera Ready. Available on OpenReview at https://openreview.net/forum?id=Hkl1iRNFwS

Low-Resource Knowledge-Grounded Dialogue Generation

Xueliang Zhao, Wei Wu, Chongyang Tao, Can Xu, Dongyan Zhao, Rui Yan

Comments Published in ICLR 2020

Discriminative Particle Filter Reinforcement Learning for Complex Partial Observations

Xiao Ma, Peter Karkus, David Hsu, Wee Sun Lee, Nan Ye

Comments Accepted to ICLR 2020

The Break-Even Point on Optimization Trajectories of Deep Neural Networks

Stanislaw Jastrzebski, Maciej Szymczak, Stanislav Fort, Devansh Arpit, Jacek Tabor, Kyunghyun Cho, Krzysztof Geras

Comments Accepted as a spotlight at ICLR 2020. The last two authors contributed equally

Non-Autoregressive Dialog State Tracking

Hung Le, Richard Socher, Steven C. H. Hoi

Comments Accepted at ICLR 2020. International Conference on Learning Representations (2020)

AtomNAS: Fine-Grained End-to-End Neural Architecture Search

Jieru Mei, Yingwei Li, Xiaochen Lian, Xiaojie Jin, Linjie Yang, Alan Yuille, Jianchao Yang

Comments ICLR 2020 camera ready version

Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators

Reinhard Heckel, Mahdi Soltanolkotabi

Comments final ICRL version; simplifications in the proof

Journal ref International Conference on Learning Representations (ICLR) 2020

Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds

Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, Alekh Agarwal

Journal ref 2020 International Conference on Learning Representations

Unpaired Point Cloud Completion on Real Scans using Adversarial Training

Xuelin Chen, Baoquan Chen, Niloy J. Mitra

Comments ICLR 2020

Learning to Plan in High Dimensions via Neural Exploration-Exploitation Trees

Binghong Chen, Bo Dai, Qinjie Lin, Guo Ye, Han Liu, Le Song

Comments 26 pages, 74 figures, ICLR 2020 spotlight

Temporal Difference Models: Model-Free Deep RL for Model-Based Control

Vitchyr Pong, Shixiang Gu, Murtaza Dalal, Sergey Levine

Comments Appeared in ICLR 2018; typos corrected

GenDICE: Generalized Offline Estimation of Stationary Values

Ruiyi Zhang, Bo Dai, Lihong Li, Dale Schuurmans

Comments ICLR 2020

Learning to Represent Programs with Property Signatures

Augustus Odena, Charles Sutton

Comments ICLR 2020