ICML

Understanding Instance-Level Label Noise: Disparate Impacts and Treatments

Yang Liu

Comments Accepted to ICML 2021 as a long talk paper

Generalized Doubly Reparameterized Gradient Estimators

Matthias Bauer, Andriy Mnih

Journal ref 38th International Conference on Machine Learning (ICML 2021)

Toward Better Generalization Bounds with Locally Elastic Stability

Zhun Deng, Hangfeng He, Weijie J. Su

Comments Published in ICML 2021

Notes on the Behavior of MC Dropout

Francesco Verdoja, Ville Kyrki

Comments Presented at the ICML 2021 Workshop on "Uncertainty and Robustness in Deep Learning"

T-Basis: a Compact Representation for Neural Networks

Anton Obukhov, Maxim Rakhuba, Stamatios Georgoulis, Menelaos Kanakis, Dengxin Dai, Luc Van Gool

Comments Accepted at ICML 2020

Nonlinear Least Squares for Large-Scale Machine Learning using Stochastic Jacobian Estimates

Johannes J. Brust

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021

Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing

Kaixin Wang, Kuangqi Zhou, Qixin Zhang, Jie Shao, Bryan Hooi, Jiashi Feng

Comments ICML 2021

What Makes for End-to-End Object Detection?

Peize Sun, Yi Jiang, Enze Xie, Wenqi Shao, Zehuan Yuan, Changhu Wang, Ping Luo

Comments ICML version

BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysis

Hejie Cui, Wei Dai, Yanqiao Zhu, Xiaoxiao Li, Lifang He, Carl Yang

Comments This paper has been accepted to ICML 2021 Workshop on Interpretable Machine Learning in Healthcare

SVP-CF: Selection via Proxy for Collaborative Filtering Data

Noveen Sachdeva, Carole-Jean Wu, Julian McAuley

Comments 11 pages, 3 figures, accepted at the SubSetML workshop at ICML '21 (Link: https://sites.google.com/view/icml-2021-subsetml/home)

Self-Attentive Ensemble Transformer: Representing Ensemble Interactions in Neural Networks for Earth System Models

Tobias Sebastian Finn

Comments 7 Pages, 4 Figures, Accepted at the ICML 2021 workshop "Tackling Climate Change with Machine Learning", Code to the paper: https://github.com/tobifinn/ensemble_transformer

Data efficiency in graph networks through equivariance

Francesco Farina, Emma Slade

Comments Presented at the ICML 2021 Workshop on Subset Selection in Machine Learning: From Theory to Practice. arXiv admin note: text overlap with arXiv:2105.14058

The DEformer: An Order-Agnostic Distribution Estimating Transformer

Michael A. Alcorn, Anh Nguyen

Comments Poster at the Third Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models (ICML 2021)

Online Learning with Optimism and Delay

Genevieve Flaspohler, Francesco Orabona, Judah Cohen, Soukayna Mouatadid, Miruna Oprescu, Paulo Orenstein, Lester Mackey

Comments ICML 2021. 9 pages of main paper and 26 pages of appendix text

Nondeterminism and Instability in Neural Network Optimization

Cecilia Summers, Michael J. Dinneen

Comments ICML 2021

Confidence-Budget Matching for Sequential Budgeted Learning

Yonathan Efroni, Nadav Merlis, Aadirupa Saha, Shie Mannor

Comments Accepted to ICML 2021

Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning

Taehyeong Kim, Injune Hwang, Hyundo Lee, Hyunseo Kim, Won-Seok Choi, Joseph J. Lim, Byoung-Tak Zhang

Comments Accepted to ICML 2021

General Invertible Transformations for Flow-based Generative Modeling

Jakub M. Tomczak

Comments Code: https://github.com/jmtomczak/git_flow, accepted to INNF+ 2021 at ICML

Simple and Effective VAE Training with Calibrated Decoders

Oleh Rybkin, Kostas Daniilidis, Sergey Levine

Comments International Conference on Machine Learning (ICML), 2021. Project website is at https://orybkin.github.io/sigma-vae/

Accelerating Safe Reinforcement Learning with Constraint-mismatched Policies

Tsung-Yen Yang, Justinian Rosca, Karthik Narasimhan, Peter J. Ramadge

Comments International Conference on Machine Learning (ICML) 2021

Re-understanding Finite-State Representations of Recurrent Policy Networks

Mohamad H. Danesh, Anurag Koul, Alan Fern, Saeed Khorram

Comments ICML 2021

Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression

Vincent Mai, Waleed Khamies, Liam Paull

Comments Accepted at the Uncertainty in Deep Learning (UDL) workshop at ICML 2021

Continual Learning in the Teacher-Student Setup: Impact of Task Similarity

Sebastian Lee, Sebastian Goldt, Andrew Saxe

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6109-6119, 2021

Towards Rigorous Interpretations: a Formalisation of Feature Attribution

Darius Afchar, Romain Hennequin, Vincent Guigue

Comments 38th International Conference on Machine Learning (ICML 2021)

Journal ref PMLR 139:76-86, 2021

A Sampling-Based Method for Tensor Ring Decomposition

Osman Asif Malik, Stephen Becker

Comments Accepted to ICML 2021

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7400-7411, 2021

Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks

Eli A. Meirom, Haggai Maron, Shie Mannor, Gal Chechik

Comments ICML 2021

Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability

Kaizhao Liang, Jacky Y. Zhang, Boxin Wang, Zhuolin Yang, Oluwasanmi Koyejo, Bo Li

Comments Accepted to ICML 2021

Imitation by Predicting Observations

Andrew Jaegle, Yury Sulsky, Arun Ahuja, Jake Bruce, Rob Fergus, Greg Wayne

Comments ICML 2021

Matrix Sketching for Secure Collaborative Machine Learning

Mengjiao Zhang, Shusen Wang

Comments In International Conference on Machine Learning (ICML), 2021

Probabilistic Time Series Forecasting with Implicit Quantile Networks

Adèle Gouttes, Kashif Rasul, Mateusz Koren, Johannes Stephan, Tofigh Naghibi

Comments Accepted at the ICML 2021 Time Series Workshop