ICML

Rethinking Positive Aggregation and Propagation of Gradients in Gradient-based Saliency Methods

Ashkan Khakzar, Soroosh Baselizadeh, Nassir Navab

Comments ICML 2020 - Workshop on Human Interpretability in Machine Learning - Spotlight paper - Video at http://whi2020.online/poster_40.html

Enhance CNN Robustness Against Noises for Classification of 12-Lead ECG with Variable Length

Linhai Ma, Liang Liang

Comments This paper is accepted by 19TH IEEE International Conference on Machine Learning and Applications (ICMLA2020)

Covariate Distribution Aware Meta-learning

Amrith Setlur, Saket Dingliwal, Barnabas Poczos

Journal ref ICML 2020 Lifelong Learning Workshop

On Learning Sets of Symmetric Elements

Haggai Maron, Or Litany, Gal Chechik, Ethan Fetaya

Comments 37th International Conference on Machine Learning, Vienna,2020, Outstanding paper award

Semi-Supervised StyleGAN for Disentanglement Learning

Weili Nie, Tero Karras, Animesh Garg, Shoubhik Debnath, Anjul Patney, Ankit B. Patel, Anima Anandkumar

Comments ICML 2020, 21 pages. Project page: https://sites.google.com/nvidia.com/semi-stylegan

GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values

Shangtong Zhang, Bo Liu, Shimon Whiteson

Comments ICML 2020

Provable Low Rank Phase Retrieval

Seyedehsara Nayer, Praneeth Narayanamurthy, Namrata Vaswani

Comments A short version of this work is in ICML 2019, this longer version is published in IEEE Trans. Info. Th on March 2020. Fixing minor but important errors in Lemmas 3.10, 3.11, 3.12 statements and in proof of the Term1 bound. No change to Theorem statement

Reconstruction Bottlenecks in Object-Centric Generative Models

Martin Engelcke, Oiwi Parker Jones, Ingmar Posner

Comments 10 pages, 7 Figures, Workshop on Object-Oriented Learning at ICML 2020

Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation

Shangtong Zhang, Bo Liu, Hengshuai Yao, Shimon Whiteson

Comments ICML 2020

An Optimistic Perspective on Offline Reinforcement Learning

Rishabh Agarwal, Dale Schuurmans, Mohammad Norouzi

Comments ICML 2020. An earlier version was titled "Striving for Simplicity in Off-Policy Deep Reinforcement Learning". Project Website: https://offline-rl.github.io

Journal ref Proceedings of the 37th International Conference on Machine Learning, PMLR 119:104-114, 2020

Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks

Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu, Adish Singla

Comments Journal version of ICML'20 paper. New theoretical results for jointly poisoning rewards and transitions

Identifying Missing Component in the Bechdel Test Using Principal Component Analysis Method

Raghav Lakhotia, Chandra Kanth Nagesh, Krishna Madgula

Comments 8 pages, 6 images, Published in the Proceedings of International Conference on Machine Learning and Applications (ICMLA), 324 - 331, June 2019, Copenhagen, Denmark, Recipient of the Best Paper Award

Journal ref World Academy of Science, Engineering and Technology International Journal of Computer and Systems Engineering Vol:13, No:6, 2019

PaccMann$^{RL}$ on SARS-CoV-2: Designing antiviral candidates with conditional generative models

Jannis Born, Matteo Manica, Joris Cadow, Greta Markert, Nil Adell Mill, Modestas Filipavicius, María Rodríguez Martínez

Comments 5 pages, 6 figures

Journal ref ICML Workshop on Computational Biology 2020

Improving Generalization by Controlling Label-Noise Information in Neural Network Weights

Hrayr Harutyunyan, Kyle Reing, Greg Ver Steeg, Aram Galstyan

Comments ICML, 2020

Estimating conditional density of missing values using deep Gaussian mixture model

Marcin Przewięźlikowski, Marek Śmieja, Łukasz Struski

Comments A preliminary version of this paper appeared as an extended abstract at the ICML 2020 Workshop on The Art of Learning with Missing Values

Stochastic Gradient and Langevin Processes

Xiang Cheng, Dong Yin, Peter L. Bartlett, Michael I. Jordan

Comments ICML 2020, code available at https://github.com/dongyin92/noise_covariance

Efficient Full-Matrix Adaptive Regularization

Naman Agarwal, Brian Bullins, Xinyi Chen, Elad Hazan, Karan Singh, Cyril Zhang, Yi Zhang

Comments Updated to ICML 2019 camera-ready version. Title of preprint was "The Case for Full-Matrix Adaptive Regularization"

Coresets for Data-efficient Training of Machine Learning Models

Baharan Mirzasoleiman, Jeff Bilmes, Jure Leskovec

Journal ref International Conference on Machine Learning 2020

Towards Understanding the Regularization of Adversarial Robustness on Neural Networks

Yuxin Wen, Shuai Li, Kui Jia

Comments Published as a conference paper at ICML 2020

Piecewise Linear Regression via a Difference of Convex Functions

Ali Siahkamari, Aditya Gangrade, Brian Kulis, Venkatesh Saligrama

Comments Published in International Conference on Machine Learning (ICML2020) Proceedings

Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules

Sarthak Mittal, Alex Lamb, Anirudh Goyal, Vikram Voleti, Murray Shanahan, Guillaume Lajoie, Michael Mozer, Yoshua Bengio

Comments ICML 2020

Predicting Length of Stay in the Intensive Care Unit with Temporal Pointwise Convolutional Networks

Emma Rocheteau, Pietro Liò, Stephanie Hyland

Comments Machine Learning for Health (ML4H) at NeurIPS 2020 - Extended Abstract. Also accepted for spotlight presentation at Healthcare Systems, Population Health, and the Role of Health-Tech (HSYS) at ICML 2020. The full length version of this paper can be found at arXiv:2007.09483

Sparse Perturbations for Improved Convergence in Stochastic Zeroth-Order Optimization

Mayumi Ohta, Nathaniel Berger, Artem Sokolov, Stefan Riezler

Comments International Conference on Machine Learning, Optimization, and Data Science (LOD), Siena, Italy

Journal ref LOD 2020

Cosine Similarity of Multimodal Content Vectors for TV Programmes

Saba Nazir, Taner Cagali, Chris Newell, Mehrnoosh Sadrzadeh

Comments 3 pages, 1 figure, Machine Learning for Media Discovery (ML4MD) Workshop at ICML 2020

Towards Obfuscated Malware Detection for Low Powered IoT Devices

Daniel Park, Hannah Powers, Benji Prashker, Leland Liu, Bülent Yener

Comments preprint. to appear at the International Conference on Machine Learning Applications (ICMLA) 2020

Feature Noise Induces Loss Discrepancy Across Groups

Fereshte Khani, Percy Liang

Comments ICML 2020

Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations

Wu Lin, Mohammad Emtiyaz Khan, Mark Schmidt

Comments Corrected some typos and updated the appendix (ICML 2019)

Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: A Joint Gradient Estimation and Tracking Approach

Haoran Sun, Songtao Lu, Mingyi Hong

Journal ref Published at the International Conference on Machine Learning (ICML 2020)

Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise

Umut Şimşekli, Lingjiong Zhu, Yee Whye Teh, Mert Gürbüzbalaban

Comments 20 pages, Published at International Conference on Machine Learning 2020

Generalization to New Actions in Reinforcement Learning

Ayush Jain, Andrew Szot, Joseph J. Lim

Comments ICML 2020. Videos and code: https://sites.google.com/view/action-generalization