ICML

The Calibration Generalization Gap

A. Michael Carrell, Neil Mallinar, James Lucas, Preetum Nakkiran

Comments Appeared at ICML 2022 Workshop on Distribution-Free Uncertainty Quantification

Beyond Hard Labels: Investigating data label distributions

Vasco Grossmann, Lars Schmarje, Reinhard Koch

Comments https://icml.cc/virtual/2022/workshop/13477

Journal ref ICML 2022 Workshop DataPerf: Benchmarking Data for Data-Centric AI

Supernet Training for Federated Image Classification under System Heterogeneity

Taehyeon Kim, Se-Young Yun

Comments Oral paper on ICML 22 Workshop: "Dynamic Neural Networks"; Under review

The Influence of Explainable Artificial Intelligence: Nudging Behaviour or Boosting Capability?

Matija Franklin

Comments Accepted at the ICML-22 Workshop on Human-Machine Collaboration and Teaming held at the Thirty-ninth International Conference on Machine Learning (ICML-22), 7 pages

A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games

Wei Xiong, Han Zhong, Chengshuai Shi, Cong Shen, Tong Zhang

Comments Accepted to ICML 2022

Type theory in human-like learning and inference

Felix A. Sosa, Tomer Ullman

Comments 5 pages, 0 figures, accepted into Beyond Bayes ICML '22

Argumentative Reward Learning: Reasoning About Human Preferences

Francis Rhys Ward, Francesco Belardinelli, Francesca Toni

Comments 4 pages, ICML HMCaT workshop

MultiScale MeshGraphNets

Meire Fortunato, Tobias Pfaff, Peter Wirnsberger, Alexander Pritzel, Peter Battaglia

Journal ref 2nd AI4Science Workshop at the 39th International Conference on Machine Learning (ICML), 2022

A Neural Model for Regular Grammar Induction

Peter Belcák, David Hofer, Roger Wattenhofer

Comments Accepted to the 21st IEEE International Conference on Machine Learning and Applications (ICMLA) 2022, 6 pages, 4 figures

Fast Composite Optimization and Statistical Recovery in Federated Learning

Yajie Bao, Michael Crawshaw, Shan Luo, Mingrui Liu

Comments This is a revised version to fix the imprecise statements about linear speedup from the ICML proceedings. We use another averaging scheme for the returned solutions in Theorem 2.1 and 3.1 to guarantee linear speedup when the number of iterations is large

Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy Optimization

Minghuan Liu, Zhengbang Zhu, Yuzheng Zhuang, Weinan Zhang, Jianye Hao, Yong Yu, Jun Wang

Comments 22 pages, 3 tables, 17 figures. Published at ICML 2022. Project page and code at https://decoupled-policy-optimization.github.io/

Reward Shaping for User Satisfaction in a REINFORCE Recommender

Konstantina Christakopoulou, Can Xu, Sai Zhang, Sriraj Badam, Trevor Potter, Daniel Li, Hao Wan, Xinyang Yi, Ya Le, Chris Berg, Eric Bencomo Dixon, Ed H. Chi, Minmin Chen

Comments Accepted in Reinforcement Learning for Real Life (RL4RealLife) Workshop in the 38th International Conference on Machine Learning, 2021

FLOWGEN: Fast and slow graph generation

Aman Madaan, Yiming Yang

Comments Accepted at Dynamic Neural Networks Workshop (DyNN), ICML 2022

Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension

Bruno Loureiro, Cédric Gerbelot, Maria Refinetti, Gabriele Sicuro, Florent Krzakala

Comments 17 pages + Appendix

Journal ref Proceedings of the 39th International Conference on Machine Learning (ICML). PMLR 162:14283-14314, 2022

ButterflyFlow: Building Invertible Layers with Butterfly Matrices

Chenlin Meng, Linqi Zhou, Kristy Choi, Tri Dao, Stefano Ermon

Comments ICML 2022

MolGAN: An implicit generative model for small molecular graphs

Nicola De Cao, Thomas Kipf

Comments Code at https://github.com/nicola-decao/MolGAN

Journal ref ICML 2018 workshop on Theoretical Foundations and Applications of Deep Generative Models

Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt

Sören Mindermann, Jan Brauner, Muhammed Razzak, Mrinank Sharma, Andreas Kirsch, Winnie Xu, Benedikt Höltgen, Aidan N. Gomez, Adrien Morisot, Sebastian Farquhar, Yarin Gal

Comments ICML 2022

Federated Learning with Label Distribution Skew via Logits Calibration

Jie Zhang, Zhiqi Li, Bo Li, Jianghe Xu, Shuang Wu, Shouhong Ding, Chao Wu

Comments Accepted at ICML 2022

Data Efficient Human Intention Prediction: Leveraging Neural Network Verification and Expert Guidance

Ruixuan Liu, Changliu Liu

Comments ICML 2021 Workshop of Human in the Loop Learning

Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization

Xue Yang, Gefan Zhang, Xiaojiang Yang, Yue Zhou, Wentao Wang, Jin Tang, Tao He, Junchi Yan

Comments 19 pages, 11 figures, 16 tables, accepted by TPAMI 2022. Journal extension for GWD (ICML'21) and KLD (NeurIPS'21). arXiv admin note: text overlap with arXiv:2101.11952

Exploiting Independent Instruments: Identification and Distribution Generalization

Sorawit Saengkyongam, Leonard Henckel, Niklas Pfister, Jonas Peters

Comments Accepted at ICML 2022

Variational Inference for Infinitely Deep Neural Networks

Achille Nazaret, David Blei

Comments Published at ICML 2022

Fast-Image2Point: Towards Real-Time Point Cloud Reconstruction of a Single Image using 3D Supervision

AmirHossein Zamani, Amir G. Aghdam, Kamran Ghaffari T

Comments 1- The paper has 8 pages 2- The paper has already been accepted in IEEE International Conference on Machine Learning and Applications (ICMLA) 2022 and it will appear in IEEE ICMLA 2022 proceedings

Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments

Ryan Sullivan, J. K. Terry, Benjamin Black, John P. Dickerson

Comments Accepted at ICML 2022 Camera-Ready Version

Probabilistic Dalek -- Emulator framework with probabilistic prediction for supernova tomography

Wolfgang Kerzendorf, Nutan Chen, Jack O'Brien, Johannes Buchner, Patrick van der Smagt

Comments 7 pages, accepted at ICML 2022 Workshop on Machine Learning for Astrophysics

A Simple Guard for Learned Optimizers

Isabeau Prémont-Schwarz, Jaroslav Vítků, Jan Feyereisl

Comments 8 pages main article, 19 figures total, 2 pages of references, 7 pages of appendix. ICML 2022. Added Appendix Section H with extra experiments about stability

Journal ref In Proc. 39th International Conference on Machine Learning (ICML 2022)

Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks

Noam Razin, Asaf Maman, Nadav Cohen

Comments Accepted to ICML 2022

Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks

Litian Liang, Yaosheng Xu, Stephen McAleer, Dailin Hu, Alexander Ihler, Pieter Abbeel, Roy Fox

Journal ref ICML 2022

Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask

Sheng-Chun Kao, Amir Yazdanbakhsh, Suvinay Subramanian, Shivani Agrawal, Utku Evci, Tushar Krishna

Comments 11 pages, 2 figures, and 9 tables. Published at the ICML Workshop on Sparsity in Neural Networks Advancing Understanding and Practice, 2022. First two authors contributed equally

Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations

Bodhisattwa Prasad Majumder, Oana-Maria Camburu, Thomas Lukasiewicz, Julian McAuley

Comments Accepted in ICML 2022 as a spotlight