ICML

Non-exponentially weighted aggregation: regret bounds for unbounded loss functions

Pierre Alquier

Journal ref Proceedings of the 38th International Conference on Machine Learning, Proceedings of Machine Learning Research, 2021, vol. 139, pp. 207-218

Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs

Tolga Ergen, Mert Pilanci

Comments Accepted to ICML 2021

Pointwise Binary Classification with Pairwise Confidence Comparisons

Lei Feng, Senlin Shu, Nan Lu, Bo Han, Miao Xu, Gang Niu, Bo An, Masashi Sugiyama

Comments Accepted to ICML 2021

Fractal Gaussian Networks: A sparse random graph model based on Gaussian Multiplicative Chaos

Subhroshekhar Ghosh, Krishnakumar Balasubramanian, Xiaochuan Yang

Comments Accepted for publication at IEEE Transactions on Information Theory. A shorter version of this work appeared at the International Conference on Machine Learning (ICML 2020)

A Contrastive Learning Approach to Auroral Identification and Classification

Jeremiah W. Johnson, Swathi Hari, Donald Hampton, Hyunju K. Connor, Amy Keesee

Comments 6 pages, 5 figures, 1 table

Journal ref Proceedings of the 20th IEEE International Conference on Machine Learning and Applications, Dec. 2021

Optimization Planning for 3D ConvNets

Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Tao Mei

Comments ICML 2021; Code is publicly available at: https://github.com/ZhaofanQiu/Optimization-Planning-for-3D-ConvNets

MARINA: Faster Non-Convex Distributed Learning with Compression

Eduard Gorbunov, Konstantin Burlachenko, Zhize Li, Peter Richtárik

Comments ICML 2021; v2 contains additional experiments; v3 contains small fixes of the typos in the complexity results for online case for VR-MARINA; 42 pages, 6 figures, 3 algorithms

Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks

Péter Mernyei, Cătălina Cangea

Comments Graph Representation Learning and Beyond workshop (ICML 2020); corrected incorrect metrics due to issue in experiment implementation

Forecasting emissions through Kaya identity using Neural Ordinary Differential Equations

Pierre Browne, Aranildo Lima, Rossella Arcucci, César Quilodrán-Casas

Comments 5 pages, 2 figures, Tackling Climate Change with Machine Learning workshop at ICML 2021

Optimal Transport using GANs for Lineage Tracing

Neha Prasad, Karren Yang, Caroline Uhler

Comments 4 pages excluding references, 2 figures, 3 tables. Accepted at ICML 2020 Workshop on Computational Biology for Spotlight Presentation. Code can be found here: https://github.com/uhlerlab/superot

SAFL: A Self-Attention Scene Text Recognizer with Focal Loss

Bao Hieu Tran, Thanh Le-Cong, Huu Manh Nguyen, Duc Anh Le, Thanh Hung Nguyen, Phi Le Nguyen

Comments Accepted to ICMLA 2020

Journal ref 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA)

When are Iterative Gaussian Processes Reliably Accurate?

Wesley J. Maddox, Sanyam Kapoor, Andrew Gordon Wilson

Comments ICML 2021 OPTML Workshop

Local Quadratic Convergence of Stochastic Gradient Descent with Adaptive Step Size

Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

Comments ICML 2021 Workshop on Beyond first-order methods in ML systems

Differentially-Private Clustering of Easy Instances

Edith Cohen, Haim Kaplan, Yishay Mansour, Uri Stemmer, Eliad Tsfadia

Comments A preliminary version appeared in ICML 2021

Monte Carlo EM for Deep Time Series Anomaly Detection

François-Xavier Aubet, Daniel Zügner, Jan Gasthaus

Comments Presented at the ICML 2021 Time Series Workshop

Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations

Angeliki Kamoutsi, Goran Banjac, John Lygeros

Journal ref International Conference of Machine Learning (ICML) 2021

Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies

Paul Vicol, Luke Metz, Jascha Sohl-Dickstein

Comments ICML 2021

NFTGAN: Non-Fungible Token Art Generation Using Generative Adversarial Networks

Sakib Shahriar, Kadhim Hayawi

Comments Submitted to the 7th International Conference on Machine Learning Technologies

Practical Active Learning with Model Selection for Small Data

Maryam Pardakhti, Nila Mandal, Anson W. K. Ma, Qian Yang

Comments Accepted for publication in the Proceedings of the 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)

Offline Planning and Online Learning under Recovering Rewards

David Simchi-Levi, Zeyu Zheng, Feng Zhu

Comments v1 accepted by ICML 2021

DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning

Wei-Fang Sun, Cheng-Kuang Lee, Chun-Yi Lee

Comments ICML 2021

Preselection Bandits

Viktor Bengs, Eyke Hüllermeier

Journal ref Proceedings of the 37th International Conference on Machine Learning (ICML 2020). Volume 119 of the Proceedings of Machine Learning Research (PMLR), pages 778-787

Enhanced Object Detection in Floor-plan through Super Resolution

Dev Khare, N S Kamal, Barathi Ganesh HB, V Sowmya, V V Sajith Variyar

Comments 3rd International Conference on Machine Learning, Image Processing, Network Security and Data Sciences

Quantum Algorithms for Reinforcement Learning with a Generative Model

Daochen Wang, Aarthi Sundaram, Robin Kothari, Ashish Kapoor, Martin Roetteler

Comments 26 pages

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10916-10926, 2021

Smooth $p$-Wasserstein Distance: Structure, Empirical Approximation, and Statistical Applications

Sloan Nietert, Ziv Goldfeld, Kengo Kato

Comments updated to match ICML 2021 paper

Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics

Vivek Jayaram, John Thickstun

Comments 16 pages, 7 figures, ICML 2021

TREX: Tree-Ensemble Representer-Point Explanations

Jonathan Brophy, Daniel Lowd

Comments 11 pages, 7 figures, and 4 tables. XXAI 2020 (co-located with ICML)

The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks

Bohan Wang, Qi Meng, Wei Chen, Tie-Yan Liu

Comments ICML 2021 Long Talk

Uncertainty-Aware (UNA) Bases for Deep Bayesian Regression Using Multi-Headed Auxiliary Networks

Sujay Thakur, Cooper Lorsung, Yaniv Yacoby, Finale Doshi-Velez, Weiwei Pan

Comments Accepted at ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning

Neighborhood Random Walk Graph Sampling for Regularized Bayesian Graph Convolutional Neural Networks

Aneesh Komanduri, Justin Zhan

Comments Accepted for publication at the 20th IEEE International Conference on Machine Learning and Applications (ICMLA 2021)