ICML

T-GD: Transferable GAN-generated Images Detection Framework

Hyeonseong Jeon, Youngoh Bang, Junyaup Kim, Simon S. Woo

Comments ICML 2020

DQI: A Guide to Benchmark Evaluation

Swaroop Mishra, Anjana Arunkumar, Bhavdeep Sachdeva, Chris Bryan, Chitta Baral

Comments ICML UDL 2020

scGNN: scRNA-seq Dropout Imputation via Induced Hierarchical Cell Similarity Graph

Kexin Huang

Comments Accepted to ICML 2020 Workshop on Computational Biology

Accelerated Stochastic Gradient-free and Projection-free Methods

Feihu Huang, Lue Tao, Songcan Chen

Comments Accepted to ICML 2020, 34 pages

Improved Sleeping Bandits with Stochastic Actions Sets and Adversarial Rewards

Aadirupa Saha, Pierre Gaillard, Michal Valko

Comments Accepted to ICML 2020

On Leveraging Pretrained GANs for Generation with Limited Data

Miaoyun Zhao, Yulai Cong, Lawrence Carin

Comments Accepted at ICML 2020

Stronger and Faster Wasserstein Adversarial Attacks

Kaiwen Wu, Allen Houze Wang, Yaoliang Yu

Comments 30 pages, accepted to ICML 2020

An Integer Programming Approach to Deep Neural Networks with Binary Activation Functions

Bubacarr Bah, Jannis Kurtz

Journal ref Workshop on Beyond first-order methods in ML systems at the 37th International Conference on Machine Learning, Vienna, Austria, 2020

Stochastic Latent Residual Video Prediction

Jean-Yves Franceschi, Edouard Delasalles, Mickaël Chen, Sylvain Lamprier, Patrick Gallinari

Journal ref Thirty-seventh International Conference on Machine Learning, International Machine Learning Society, Jul 2020, Vienne, Austria. pp.89--102

Variational Autoencoders with Riemannian Brownian Motion Priors

Dimitris Kalatzis, David Eklund, Georgios Arvanitidis, Søren Hauberg

Comments Published in ICML 2020

Journal ref Proceedings of the 37th International Conference on Machine Learning, Vienna, Austria, PMLR 119, 2020

InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs

Zinan Lin, Kiran Koshy Thekumparampil, Giulia Fanti, Sewoong Oh

Comments Published in ICML 2020. 45 pages, 52 figures, a new unsupervised model selection scheme (ModelCentrality) is introduced in this version

On Variational Learning of Controllable Representations for Text without Supervision

Peng Xu, Jackie Chi Kit Cheung, Yanshuai Cao

Comments ICML 2020 Camera Ready. Previous title: Unsupervised Controllable Text Generation with Global Variation Discovery and Disentanglement

Hierarchical Protein Function Prediction with Tail-GNNs

Stefan Spalević, Petar Veličković, Jovana Kovačević, Mladen Nikolić

Journal ref ICML 2020 - Workshops - Graph RepresGraph Representation Learning and Beyond (GRL+)

Momentum-Based Policy Gradient Methods

Feihu Huang, Shangqian Gao, Jian Pei, Heng Huang

Comments ICML 2020, 24 pages

Learning and Sampling of Atomic Interventions from Observations

Arnab Bhattacharyya, Sutanu Gayen, Saravanan Kandasamy, Ashwin Maran, N. V. Vinodchandran

Comments 26 pages, 4 figures, a version appeared in ICML 2020

Thompson Sampling via Local Uncertainty

Zhendong Wang, Mingyuan Zhou

Comments ICML 2020

Circuit-Based Intrinsic Methods to Detect Overfitting

Satrajit Chatterjee, Alan Mishchenko

Comments 37th International Conference on Machine Learning held as a virtual conference on July 12-18, 2020

Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Search

Yong Guo, Yaofo Chen, Yin Zheng, Peilin Zhao, Jian Chen, Junzhou Huang, Mingkui Tan

Comments Accepted by ICML 2020

Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks

Francesco Croce, Matthias Hein

Comments In ICML 2020

LP-SparseMAP: Differentiable Relaxed Optimization for Sparse Structured Prediction

Vlad Niculae, André F. T. Martins

Comments 34 pages, 5 tables, 4 figures. ICML 2020

Musical Word Embedding: Bridging the Gap between Listening Contexts and Music

Seungheon Doh, Jongpil Lee, Tae Hong Park, Juhan Nam

Comments Machine Learning for Media Discovery Workshop, International Conference on Machine Learning (ICML), 2020

Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations

Florian Tramèr, Jens Behrmann, Nicholas Carlini, Nicolas Papernot, Jörn-Henrik Jacobsen

Comments ICML 2020 (Supersedes the workshop paper "Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness", arXiv:1903.10484)

Skew-Fit: State-Covering Self-Supervised Reinforcement Learning

Vitchyr H. Pong, Murtaza Dalal, Steven Lin, Ashvin Nair, Shikhar Bahl, Sergey Levine

Comments ICML 2020. 8 pages, 8 figures; 9 pages appendix (6 additional figures)

Low-loss connection of weight vectors: distribution-based approaches

Ivan Anokhin, Dmitry Yarotsky

Comments accepted to ICML 2020

An Accelerated DFO Algorithm for Finite-sum Convex Functions

Yuwen Chen, Antonio Orvieto, Aurelien Lucchi

Comments 48 pages, 44 figures; Proceedings of the 37th International Conference on Machine Learning, Vienna, Austria, PMLR 119, 2020

Tight Bounds on Minimax Regret under Logarithmic Loss via Self-Concordance

Blair Bilodeau, Dylan J. Foster, Daniel M. Roy

Comments 25 pages

Journal ref Proceedings of the 37th International Conference on Machine Learning, ICML 2020

Revisiting Training Strategies and Generalization Performance in Deep Metric Learning

Karsten Roth, Timo Milbich, Samarth Sinha, Prateek Gupta, Björn Ommer, Joseph Paul Cohen

Comments ICML 2020. Main paper 8.25 pages, 26 pages total

Regularized Optimal Transport is Ground Cost Adversarial

François-Pierre Paty, Marco Cuturi

Journal ref ICML 2020

Choice Set Optimization Under Discrete Choice Models of Group Decisions

Kiran Tomlinson, Austin R. Benson

Comments 19 pages, 7 figures. ICML 2020. This is an updated version after reviews

Thompson Sampling Algorithms for Mean-Variance Bandits

Qiuyu Zhu, Vincent Y. F. Tan

Comments 26 pages, 10 figures, ICML 2020