ICML

Improved Confidence Bounds for the Linear Logistic Model and Applications to Linear Bandits

Kwang-Sung Jun, Lalit Jain, Blake Mason, Houssam Nassif

Journal ref Proceedings of the International Conference on Machine Learning (ICML'21), pp. 5148-5157, 2021

Thresholded Lasso Bandit

Kaito Ariu, Kenshi Abe, Alexandre Proutière

Comments International Conference on Machine Learning (ICML 2022), Proceedings of Machine Learning Research

Fair Generalized Linear Models with a Convex Penalty

Hyungrok Do, Preston Putzel, Axel Martin, Padhraic Smyth, Judy Zhong

Comments Accepted for publication in ICML 2022

Path-Gradient Estimators for Continuous Normalizing Flows

Lorenz Vaitl, Kim A. Nicoli, Shinichi Nakajima, Pan Kessel

Comments 8 pages, 5 figures, 39th International Conference on Machine Learning

LIMO: Latent Inceptionism for Targeted Molecule Generation

Peter Eckmann, Kunyang Sun, Bo Zhao, Mudong Feng, Michael K. Gilson, Rose Yu

Comments 16 pages, 5 figures, ICML 2022

Robust Group Synchronization via Quadratic Programming

Yunpeng Shi, Cole Wyeth, Gilad Lerman

Comments Accepted to ICML 2022

Knowledge Base Question Answering by Case-based Reasoning over Subgraphs

Rajarshi Das, Ameya Godbole, Ankita Naik, Elliot Tower, Robin Jia, Manzil Zaheer, Hannaneh Hajishirzi, Andrew McCallum

Comments ICML 2022

Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality Features

Zhaowei Zhu, Jialu Wang, Yang Liu

Comments ICML 2022

More Efficient Sampling for Tensor Decomposition With Worst-Case Guarantees

Osman Asif Malik

Comments Accepted to ICML 2022

Detecting Corrupted Labels Without Training a Model to Predict

Zhaowei Zhu, Zihao Dong, Yang Liu

Comments ICML 2022

Popular decision tree algorithms are provably noise tolerant

Guy Blanc, Jane Lange, Ali Malik, Li-Yang Tan

Comments Proceedings of the 39 th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022

CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer

Yao Mu, Shoufa Chen, Mingyu Ding, Jianyu Chen, Runjian Chen, Ping Luo

Comments ICML 2022

Fast Lossless Neural Compression with Integer-Only Discrete Flows

Siyu Wang, Jianfei Chen, Chongxuan Li, Jun Zhu, Bo Zhang

Comments Accepted as a conference paper at International Conference on Machine Learning (ICML) 2022

Multiple-Play Stochastic Bandits with Shareable Finite-Capacity Arms

Xuchuang Wang, Hong Xie, John C. S. Lui

Comments to appear in ICML 2022

Generalised Policy Improvement with Geometric Policy Composition

Shantanu Thakoor, Mark Rowland, Diana Borsa, Will Dabney, Rémi Munos, André Barreto

Comments ICML 2022

Fast Finite Width Neural Tangent Kernel

Roman Novak, Jascha Sohl-Dickstein, Samuel S. Schoenholz

Comments Published as a conference paper at ICML 2022

Sheaf Neural Networks with Connection Laplacians

Federico Barbero, Cristian Bodnar, Haitz Sáez de Ocáriz Borde, Michael Bronstein, Petar Veličković, Pietro Liò

Comments Presented at the ICML 2022 Workshop on Topology, Algebra, and Geometry in Machine Learning

Sparse Double Descent: Where Network Pruning Aggravates Overfitting

Zheng He, Zeke Xie, Quanzhi Zhu, Zengchang Qin

Comments ICML 2022

A Deep Learning Approach for the Segmentation of Electroencephalography Data in Eye Tracking Applications

Lukas Wolf, Ard Kastrati, Martyna Beata Płomecka, Jie-Ming Li, Dustin Klebe, Alexander Veicht, Roger Wattenhofer, Nicolas Langer

Comments 21 pages, Published at the Proceedings of the 39th International Conference on Machine Learning (ICML) 2022

RECAPP: Crafting a More Efficient Catalyst for Convex Optimization

Yair Carmon, Arun Jambulapati, Yujia Jin, Aaron Sidford

Comments Accepted at ICML'22

NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation Learning

Wentao Zhang, Zeang Sheng, Mingyu Yang, Yang Li, Yu Shen, Zhi Yang, Bin Cui

Comments 17 pages, 8 figures

Journal ref ICML 2022

DFG-NAS: Deep and Flexible Graph Neural Architecture Search

Wentao Zhang, Zheyu Lin, Yu Shen, Yang Li, Zhi Yang, Bin Cui

Comments 13 pages, 7 figures

Journal ref ICML 2022

Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization

Deokjae Lee, Seungyong Moon, Junhyeok Lee, Hyun Oh Song

Comments ICML 2022; Codes at https://github.com/snu-mllab/DiscreteBlockBayesAttack

Boosting Graph Structure Learning with Dummy Nodes

Xin Liu, Jiayang Cheng, Yangqiu Song, Xin Jiang

Comments Accepted by ICML 2022

Thompson Sampling for Robust Transfer in Multi-Task Bandits

Zhi Wang, Chicheng Zhang, Kamalika Chaudhuri

Comments To appear in Proceedings of the 39th International Conference on Machine Learning (ICML-2022)

Strategic Representation

Vineet Nair, Ganesh Ghalme, Inbal Talgam-Cohen, Nir Rosenfeld

Comments ICML 2022

SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving

Linrui Zhang, Qin Zhang, Li Shen, Bo Yuan, Xueqian Wang

Comments The 1st Workshop on Safe Learning for Autonomous Driving (SL4AD) with ICML 2022

A Parametric Class of Approximate Gradient Updates for Policy Optimization

Ramki Gummadi, Saurabh Kumar, Junfeng Wen, Dale Schuurmans

Journal ref ICML 2022

Active Fairness Auditing

Tom Yan, Chicheng Zhang

Comments 34 pages; 2 figures; ICML 2022

Metric-Fair Classifier Derandomization

Jimmy Wu, Yatong Chen, Yang Liu

Comments Proceedings of ICML 2022