ICML

End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization

Shohei Taniguchi, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo

Comments Accepted at ICML 2023

Active causal structure learning with advice

Davin Choo, Themis Gouleakis, Arnab Bhattacharyya

Comments Accepted into ICML 2023

Causal Discovery with Latent Confounders Based on Higher-Order Cumulants

Ruichu Cai, Zhiyi Huang, Wei Chen, Zhifeng Hao, Kun Zhang

Comments Accepted by ICML 2023

Recasting Self-Attention with Holographic Reduced Representations

Mohammad Mahmudul Alam, Edward Raff, Stella Biderman, Tim Oates, James Holt

Comments To appear in Proceedings of the 40th International Conference on Machine Learning (ICML)

Are Large Kernels Better Teachers than Transformers for ConvNets?

Tianjin Huang, Lu Yin, Zhenyu Zhang, Li Shen, Meng Fang, Mykola Pechenizkiy, Zhangyang Wang, Shiwei Liu

Comments Accepted by ICML 2023

Journal ref ICML 2023

Deep Clustering with Incomplete Noisy Pairwise Annotations: A Geometric Regularization Approach

Tri Nguyen, Shahana Ibrahim, Xiao Fu

Comments Accepted to ICML 2023; 28 pages, 10 tables, 3 figures

Benign Overfitting in Deep Neural Networks under Lazy Training

Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos, Francesco Locatello, Volkan Cevher

Comments Accepted in ICML 2023

Trompt: Towards a Better Deep Neural Network for Tabular Data

Kuan-Yu Chen, Ping-Han Chiang, Hsin-Rung Chou, Ting-Wei Chen, Tien-Hao Chang

Comments ICML'23 (poster)

Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling

Xiaohui Chen, Jiaxing He, Xu Han, Li-Ping Liu

Comments ICML 2023, camera-ready revision

Accuracy on the Curve: On the Nonlinear Correlation of ML Performance Between Data Subpopulations

Weixin Liang, Yining Mao, Yongchan Kwon, Xinyu Yang, James Zou

Comments Accepted to the main conference of ICML 2023

Regression with Sensor Data Containing Incomplete Observations

Takayuki Katsuki, Takayuki Osogami

Comments Accepted to ICML 2023

What can online reinforcement learning with function approximation benefit from general coverage conditions?

Fanghui Liu, Luca Viano, Volkan Cevher

Comments Accepted by ICML 2023

Polarity is all you need to learn and transfer faster

Qingyang Wang, Michael A. Powell, Ali Geisa, Eric W. Bridgeford, Joshua T. Vogelstein

Comments ICML camera-ready

Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?

Boris Knyazev, Doha Hwang, Simon Lacoste-Julien

Comments ICML 2023, camera ready (7 tables with extra results added), code and models are at https://github.com/SamsungSAILMontreal/ghn3

Dropout Reduces Underfitting

Zhuang Liu, Zhiqiu Xu, Joseph Jin, Zhiqiang Shen, Trevor Darrell

Comments ICML 2023

Consistency Models

Yang Song, Prafulla Dhariwal, Mark Chen, Ilya Sutskever

Comments ICML 2023

Simple Disentanglement of Style and Content in Visual Representations

Lilian Ngweta, Subha Maity, Alex Gittens, Yuekai Sun, Mikhail Yurochkin

Comments International Conference on Machine Learning (ICML) 2023

Generalizing Neural Wave Functions

Nicholas Gao, Stephan Günnemann

Comments Published at the 40th International Conference on Machine Learning (ICML 2023)

Efficient Online Reinforcement Learning with Offline Data

Philip J. Ball, Laura Smith, Ilya Kostrikov, Sergey Levine

Comments Short Presentation at ICML 2023; to reproduce our results and use our codebase, see https://github.com/ikostrikov/rlpd

CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets

Zachary Novack, Julian McAuley, Zachary C. Lipton, Saurabh Garg

Comments Accepted at ICML 2023

Multi-View Masked World Models for Visual Robotic Manipulation

Younggyo Seo, Junsu Kim, Stephen James, Kimin Lee, Jinwoo Shin, Pieter Abbeel

Comments Accepted to ICML 2023. First two authors contributed equally. Project webpage: https://sites.google.com/view/mv-mwm

Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization

Zejia Weng, Xitong Yang, Ang Li, Zuxuan Wu, Yu-Gang Jiang

Comments 12 pages, 4 figures, ICML 2023

Unlocking Slot Attention by Changing Optimal Transport Costs

Yan Zhang, David W. Zhang, Simon Lacoste-Julien, Gertjan J. Burghouts, Cees G. M. Snoek

Comments Published at International Conference on Machine Learning (ICML) 2023

Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs

Guan-Ting Liu, En-Pei Hu, Pu-Jen Cheng, Hung-yi Lee, Shao-Hua Sun

Comments ICML 2023

General Covariance Data Augmentation for Neural PDE Solvers

Vladimir Fanaskov, Tianchi Yu, Alexander Rudikov, Ivan Oseledets

Comments accepted to ICML 2023

Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases

Xiaoxia Wu, Cheng Li, Reza Yazdani Aminabadi, Zhewei Yao, Yuxiong He

Journal ref Fortieth International Conference on Machine Learning 2023

Image Restoration with Mean-Reverting Stochastic Differential Equations

Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao, Jens Sjölund, Thomas B. Schön

Comments Accepted by ICML 2023; Project page: https://algolzw.github.io/ir-sde/index.html

Learning the Dynamics of Sparsely Observed Interacting Systems

Linus Bleistein, Adeline Fermanian, Anne-Sophie Jannot, Agathe Guilloux

Comments ICML 2023

SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning

Dongseok Shim, Seungjae Lee, H. Jin Kim

Comments ICML 2023. First two authors contributed equally. Order was determined by coin flip

Improving Graph Generation by Restricting Graph Bandwidth

Nathaniel Diamant, Alex M. Tseng, Kangway V. Chuang, Tommaso Biancalani, Gabriele Scalia

Comments Accepted at ICML 2023