ICML

Quality of Uncertainty Quantification for Bayesian Neural Network Inference

Jiayu Yao, Weiwei Pan, Soumya Ghosh, Finale Doshi-Velez

Comments Accepted to ICML UDL 2019

On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference

Rohin Shah, Noah Gundotra, Pieter Abbeel, Anca D. Dragan

Comments Published at ICML 2019

Ego-CNN: Distributed, Egocentric Representations of Graphs for Detecting Critical Structures

Ruo-Chun Tzeng, Shan-Hung Wu

Comments Proceedings of the 36th International Conference on Machine Learning

Lipschitz Generative Adversarial Nets

Zhiming Zhou, Jiadong Liang, Yuxuan Song, Lantao Yu, Hongwei Wang, Weinan Zhang, Yong Yu, Zhihua Zhang

Comments Published as a conference paper at ICML 2019

Theoretically Principled Trade-off between Robustness and Accuracy

Hongyang Zhang, Yaodong Yu, Jiantao Jiao, Eric P. Xing, Laurent El Ghaoui, Michael I. Jordan

Comments Appeared in ICML 2019; the winning methodology of the NeurIPS 2018 Adversarial Vision Challenge

Decomposing feature-level variation with Covariate Gaussian Process Latent Variable Models

Kaspar Märtens, Kieran R. Campbell, Christopher Yau

Journal ref Proceedings of the 36th International Conference on Machine Learning (ICML 2019)

A Halo Merger Tree Generation and Evaluation Framework

Sandra Robles, Jonathan S. Gómez, Adín Ramírez Rivera, Jenny A. González, Nelson D. Padilla, Diego Dujovne

Comments 11 pages, 7 figures, 2 tables, 3 appendices. Presented at the ICML 2019 Workshop on Theoretical Physics for Deep Learning

Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback

Chicheng Zhang, Alekh Agarwal, Hal Daumé, John Langford, Sahand N Negahban

Comments 42 pages, 21 figures, ICML 2019

SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning

Marvin Zhang, Sharad Vikram, Laura Smith, Pieter Abbeel, Matthew J. Johnson, Sergey Levine

Comments ICML 2019. Project website: https://sites.google.com/view/icml19solar

A Flexible Pipeline for Prediction of Tropical Cyclone Paths

Niccolò Dalmasso, Robin Dunn, Benjamin LeRoy, Chad Schafer

Comments 4 pages. The first three authors contributed equally. Presented at the ICML 2019 Workshop on "Climate Change: How can AI Help?"

TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning

Sung Whan Yoon, Jun Seo, Jaekyun Moon

Comments in proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, PMLR 97:7115-7123, 2019

Journal ref Proceedings of the 36th International Conference on Machine Learning, PMLR 97:7115-7123, 2019

MASS: Masked Sequence to Sequence Pre-training for Language Generation

Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, Tie-Yan Liu

Comments Accepted by ICML 2019

Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation

Marco Ancona, Cengiz Öztireli, Markus Gross

Comments ICML 2019

Journal ref PMLR 97 (2019) 272-281

Exploiting Structure of Uncertainty for Efficient Matroid Semi-Bandits

Pierre Perrault, Vianney Perchet, Michal Valko

Comments Accepted to ICML 2019, Long Beach

Adversarial Example Decomposition

Horace He, Aaron Lou, Qingxuan Jiang, Isay Katsman, Serge Belongie, Ser-Nam Lim

Comments ICML 2019 Workshop, Security and Privacy of Machine Learning, camera-ready version

Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits

Branislav Kveton, Csaba Szepesvari, Sharan Vaswani, Zheng Wen, Mohammad Ghavamzadeh, Tor Lattimore

Comments Proceedings of the 36th International Conference on Machine Learning

We Need No Pixels: Video Manipulation Detection Using Stream Descriptors

David Güera, Sriram Baireddy, Paolo Bestagini, Stefano Tubaro, Edward J. Delp

Comments 7 pages, 6 figures, presented at the ICML 2019 Worksop on Synthetic Realities: Deep Learning for Detecting AudioVisual Fakes

Zero-shot Learning and Knowledge Transfer in Music Classification and Tagging

Jeong Choi, Jongpil Lee, Jiyoung Park, Juhan Nam

Comments International Conference on Machine Learning (ICML) 2019, Machine Learning for Music Discovery Workshop

A Hierarchical Architecture for Sequential Decision-Making in Autonomous Driving using Deep Reinforcement Learning

Majid Moghadam, Gabriel Hugh Elkaim

Comments Appears in ICML 2019 workshop on Real-world Sequential Decision Making: Reinforcement Learning and Beyond. Source code available in: https://github.com/MajidMoghadam2006

Calibrated Model-Based Deep Reinforcement Learning

Ali Malik, Volodymyr Kuleshov, Jiaming Song, Danny Nemer, Harlan Seymour, Stefano Ermon

Journal ref Proceedings of the 36th International Conference on Machine Learning, PMLR 97:4314-4323, 2019

Cognitive Model Priors for Predicting Human Decisions

David D. Bourgin, Joshua C. Peterson, Daniel Reichman, Thomas L. Griffiths, Stuart J. Russell

Comments ICML 2019

Journal ref Proceedings of the 36th International Conference on Machine Learning, PMLR 97:5133-5141, 2019

Simplifying Graph Convolutional Networks

Felix Wu, Tianyi Zhang, Amauri Holanda de Souza, Christopher Fifty, Tao Yu, Kilian Q. Weinberger

Comments In ICML 2019. Code available at https://github.com/Tiiiger/SGC

Generalisation dynamics of online learning in over-parameterised neural networks

Sebastian Goldt, Madhu S. Advani, Andrew M. Saxe, Florent Krzakala, Lenka Zdeborová

Comments 25 pages, 13 figures

Journal ref Presented at the ICML 2019 Workshop on Theoretical Physics for Deep Learning

Transfer NAS: Knowledge Transfer between Search Spaces with Transformer Agents

Zalán Borsos, Andrey Khorlin, Andrea Gesmundo

Comments 6th ICML Workshop on Automated Machine Learning

Supervised Hierarchical Clustering with Exponential Linkage

Nishant Yadav, Ari Kobren, Nicholas Monath, Andrew McCallum

Comments Appears in ICML 2019

Characterizing Well-Behaved vs. Pathological Deep Neural Networks

Antoine Labatie

Comments Proceedings of ICML 2019 (with contact info updated and formatting issues fixed). Code available at https://github.com/alabatie/moments-dnns

Self-Similar Epochs: Value in Arrangement

Eliav Buchnik, Edith Cohen, Avinatan Hassidim, Yossi Matias

Comments 13 pages, published in ICML 2019

Analyzing the Robustness of Nearest Neighbors to Adversarial Examples

Yizhen Wang, Somesh Jha, Kamalika Chaudhuri

Journal ref International Conference on Machine Learning (ICML) 2018, Page 5133--5142

Crowdsourcing in the Absence of Ground Truth -- A Case Study

Ramya Srinivasan, Ajay Chander

Comments presented at 2019 ICML Workshop on Human in the Loop Learning (HILL 2019), Long Beach, USA

Iterative Model-Based Reinforcement Learning Using Simulations in the Differentiable Neural Computer

Adeel Mufti, Svetlin Penkov, Subramanian Ramamoorthy

Comments Accepted at the Workshop on Multi-Task and Lifelong Reinforcement Learning, 36th International Conference on Machine Learning, Long Beach, California, 2019