ICML

POEM: Out-of-Distribution Detection with Posterior Sampling

Yifei Ming, Ying Fan, Yixuan Li

Comments ICML 2022 (Long Talk); First two authors contributed equally

Journal ref Thirty-ninth International Conference on Machine Learning (2022)

Training Your Sparse Neural Network Better with Any Mask

Ajay Jaiswal, Haoyu Ma, Tianlong Chen, Ying Ding, Zhangyang Wang

Comments Accepted by ICML 2022

Statistical inference with implicit SGD: proximal Robbins-Monro vs. Polyak-Ruppert

Yoonhyung Lee, Sungdong Lee, Joong-Ho Won

Comments Accepted to the 39 th International Conference on Machine Learning. This version contains corrections to typos found after submitting the camera-ready version

Redundancy Reduction Twins Network: A Training framework for Multi-output Emotion Regression

Xin Jing, Meishu Song, Andreas Triantafyllopoulos, Zijiang Yang, Björn W. Schuller

Comments 5 pages, accepted by ICML Exvo workshop

Quantifying and Learning Linear Symmetry-Based Disentanglement

Loek Tonnaer, Luis A. Pérez Rey, Vlado Menkovski, Mike Holenderski, Jacobus W. Portegies

Comments The Thirty-ninth International Conference on Machine Learning (ICML 2022)

Utility Theory for Sequential Decision Making

Mehran Shakerinava, Siamak Ravanbakhsh

Comments ICML 2022

Structural Entropy Guided Graph Hierarchical Pooling

Junran Wu, Xueyuan Chen, Ke Xu, Shangzhe Li

Comments Accepted by ICML 2022

TACTiS: Transformer-Attentional Copulas for Time Series

Alexandre Drouin, Étienne Marcotte, Nicolas Chapados

Comments 47 pages, 33 figures, camera-ready version, Thirty-ninth International Conference on Machine Learning (ICML 2022)

Neural Tangent Kernel Analysis of Deep Narrow Neural Networks

Jongmin Lee, Joo Young Choi, Ernest K. Ryu, Albert No

Journal ref Published in International Conference on Machine Learning, 2022

Measure Estimation in the Barycentric Coding Model

Matthew Werenski, Ruijie Jiang, Abiy Tasissa, Shuchin Aeron, James M. Murphy

Comments ICML 2022

Local Augmentation for Graph Neural Networks

Songtao Liu, Rex Ying, Hanze Dong, Lanqing Li, Tingyang Xu, Yu Rong, Peilin Zhao, Junzhou Huang, Dinghao Wu

Comments Accepted by ICML'22

Prompting Decision Transformer for Few-Shot Policy Generalization

Mengdi Xu, Yikang Shen, Shun Zhang, Yuchen Lu, Ding Zhao, Joshua B. Tenenbaum, Chuang Gan

Comments ICML 2022. Project page: https://mxu34.github.io/PromptDT/

Causal Dynamics Learning for Task-Independent State Abstraction

Zizhao Wang, Xuesu Xiao, Zifan Xu, Yuke Zhu, Peter Stone

Comments International Conference on Machine Learning 2022 (ICML)

Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning

Max B. Paulus, Giulia Zarpellon, Andreas Krause, Laurent Charlin, Chris J. Maddison

Comments ICML 2022

A penalisation method for batch multi-objective Bayesian optimisation with application in heat exchanger design

Andrei Paleyes, Henry B. Moss, Victor Picheny, Piotr Zulawski, Felix Newman

Comments ICML 2022 Workshop on Adaptive Experimental Design and Active Learning in the Real World

Prisoners of Their Own Devices: How Models Induce Data Bias in Performative Prediction

José Pombal, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro

Comments ICML 2022 Workshop on Responsible Decision Making in Dynamic Environments

Revisiting Architecture-aware Knowledge Distillation: Smaller Models and Faster Search

Taehyeon Kim, Heesoo Myeong, Se-Young Yun

Comments Presented in ICML 2022 Hardware Aware Efficient Training (HAET) Workshop

Monitoring Shortcut Learning using Mutual Information

Mohammed Adnan, Yani Ioannou, Chuan-Yung Tsai, Angus Galloway, H. R. Tizhoosh, Graham W. Taylor

Comments Accepted at ICML 2022 Workshop on Spurious Correlations, Invariance, and Stability

Improving Policy Optimization with Generalist-Specialist Learning

Zhiwei Jia, Xuanlin Li, Zhan Ling, Shuang Liu, Yiran Wu, Hao Su

Comments ICML 2022

TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification

Jaeyun Song, Joonhyung Park, Eunho Yang

Comments Accepted to ICML 2022; First two authors equally contributed

Batch-Ensemble Stochastic Neural Networks for Out-of-Distribution Detection

Xiongjie Chen, Yunpeng Li, Yongxin Yang

Comments Accepted to the ICML 2022 workshop on distribution-free uncertainty quantification (DFUQ), 11 pages, 3 figures

Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis

Alexander Munteanu, Simon Omlor, Zhao Song, David P. Woodruff

Comments ICML 2022

Self-supervision and Learnable STRFs for Age, Emotion, and Country Prediction

Roshan Sharma, Tyler Vuong, Mark Lindsey, Hira Dhamyal, Rita Singh, Bhiksha Raj

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

Generating Diverse Vocal Bursts with StyleGAN2 and MEL-Spectrograms

Marco Jiralerspong, Gauthier Gidel

Comments To be published at the ICML Expressive Vocalizations Workshop and Competition (ExVo Generate) held in conjunction with the 39th International Conference on Machine Learning

PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance

Qingru Zhang, Simiao Zuo, Chen Liang, Alexander Bukharin, Pengcheng He, Weizhu Chen, Tuo Zhao

Comments Proceedings of the 39th International Conference on Machine Learning (ICML 2022)

Multitask vocal burst modeling with ResNets and pre-trained paralinguistic Conformers

Josh Belanich, Krishna Somandepalli, Brian Eoff, Brendan Jou

Comments To be published in the ICML Expressive Vocalizations Workshop & Competition 2022 (https://www.competitions.hume.ai/exvo2022)

Marginal Tail-Adaptive Normalizing Flows

Mike Laszkiewicz, Johannes Lederer, Asja Fischer

Comments Accepted at ICML2022 Thirty-ninth International Conference on Machine Learning

DECAL: DEployable Clinical Active Learning

Yash-yee Logan, Mohit Prabhushankar, Ghassan AlRegib

Comments ICML 2022 Workshop on Adaptive Experimental Design and Active Learning in the Real World

Zero-Shot AutoML with Pretrained Models

Ekrem Öztürk, Fabio Ferreira, Hadi S. Jomaa, Lars Schmidt-Thieme, Josif Grabocka, Frank Hutter

Journal ref International Conference on Machine Learning 2022

Maximum Likelihood Training for Score-Based Diffusion ODEs by High-Order Denoising Score Matching

Cheng Lu, Kaiwen Zheng, Fan Bao, Jianfei Chen, Chongxuan Li, Jun Zhu

Comments Accepted in ICML 2022