ICML

A Closer Look at the Intervention Procedure of Concept Bottleneck Models

Sungbin Shin, Yohan Jo, Sungsoo Ahn, Namhoon Lee

Comments ICML 2023

Neural Algorithmic Reasoning with Causal Regularisation

Beatrice Bevilacqua, Kyriacos Nikiforou, Borja Ibarz, Ioana Bica, Michela Paganini, Charles Blundell, Jovana Mitrovic, Petar Veličković

Comments ICML 2023, Camera Ready; 17 pages, 7 figures

PromptBoosting: Black-Box Text Classification with Ten Forward Passes

Bairu Hou, Joe O'Connor, Jacob Andreas, Shiyu Chang, Yang Zhang

Comments ICML 2023

Morse Neural Networks for Uncertainty Quantification

Benoit Dherin, Huiyi Hu, Jie Ren, Michael W. Dusenberry, Balaji Lakshminarayanan

Comments Accepted to ICML workshop on Structured Probabilistic Inference & Generative Modeling 2023

The Forward-Forward Algorithm as a feature extractor for skin lesion classification: A preliminary study

Abel Reyes-Angulo, Sidike Paheding

Comments This is a camera-ready version of the paper for the LXAI @ ICML'23 workshop

MissDiff: Training Diffusion Models on Tabular Data with Missing Values

Yidong Ouyang, Liyan Xie, Chongxuan Li, Guang Cheng

Comments 22 pages, short version is accepted by ICML workshop on Structured Probabilistic Inference & Generative Modeling 2023

When Synthetic Data Met Regulation

Georgi Ganev

Comments Accepted to the 1st Workshop on Generative AI and Law (GenLaw 2023), part of ICML 2023

Projected Tensor Power Method for Hypergraph Community Recovery

Jinxin Wang, Yuen-Man Pun, Xiaolu Wang, Peng Wang, Anthony Man-Cho So

Journal ref Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023

Hierarchical Neural Coding for Controllable CAD Model Generation

Xiang Xu, Pradeep Kumar Jayaraman, Joseph G. Lambourne, Karl D. D. Willis, Yasutaka Furukawa

Comments Accepted to ICML 2023. Project website at https://hnc-cad.github.io/

PMaF: Deep Declarative Layers for Principal Matrix Features

Zhiwei Xu, Hao Wang, Yanbin Liu, Stephen Gould

Comments 16 pages, 7 figures, 10 tables, accepted to the differentiable almost everything workshop, ICML, 2023

Differentiating Metropolis-Hastings to Optimize Intractable Densities

Gaurav Arya, Ruben Seyer, Frank Schäfer, Kartik Chandra, Alexander K. Lew, Mathieu Huot, Vikash K. Mansinghka, Jonathan Ragan-Kelley, Christopher Rackauckas, Moritz Schauer

Comments 6 pages, 6 figures; accepted at Differentiable Almost Everything Workshop of ICML 2023

Taxonomy-Structured Domain Adaptation

Tianyi Liu, Zihao Xu, Hao He, Guang-Yuan Hao, Guang-He Lee, Hao Wang

Comments Accepted by ICML 2023

Representer Point Selection for Explaining Regularized High-dimensional Models

Che-Ping Tsai, Jiong Zhang, Eli Chien, Hsiang-Fu Yu, Cho-Jui Hsieh, Pradeep Ravikumar

Comments Accepted by ICML 2023

Sharpness-Aware Minimization Alone can Improve Adversarial Robustness

Zeming Wei, Jingyu Zhu, Yihao Zhang

Comments ICML 2023 AdvML-Frontiers Workshop

Physics-Informed Localized Learning for Advection-Diffusion-Reaction Systems

Surya T. Sathujoda, Soham M. Sheth

Comments Accepted to ICML 2023 workshop on New Frontiers in Learning, Control, and Dynamical Systems

Latent Traversals in Generative Models as Potential Flows

Yue Song, T. Anderson Keller, Nicu Sebe, Max Welling

Comments ICML 2023

Graph Neural Networks with Learnable and Optimal Polynomial Bases

Yuhe Guo, Zhewei Wei

Comments Significant improvement in illustrating OptBasisGNN in Section 4. Accepted to ICML 2023(22 pages, 4 figures)

Topological Feature Selection

Antonio Briola, Tomaso Aste

Comments Accepted at the 2nd Annual Workshop on Topology, Algebra, and Geometry in Machine Learning (TAG-ML) at the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA. 2023. 23 pages, 2 figures, 13 tables

Task-Specific Skill Localization in Fine-tuned Language Models

Abhishek Panigrahi, Nikunj Saunshi, Haoyu Zhao, Sanjeev Arora

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

MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior

Jennifer J. Sun, Markus Marks, Andrew Ulmer, Dipam Chakraborty, Brian Geuther, Edward Hayes, Heng Jia, Vivek Kumar, Sebastian Oleszko, Zachary Partridge, Milan Peelman, Alice Robie, Catherine E. Schretter, Keith Sheppard, Chao Sun, Param Uttarwar, Julian M. Wagner, Eric Werner, Joseph Parker, Pietro Perona, Yisong Yue, Kristin Branson, Ann Kennedy

Comments To appear in ICML 2023, Project website: https://sites.google.com/view/computational-behavior/our-datasets/mabe2022-dataset

Thompson sampling for improved exploration in GFlowNets

Jarrid Rector-Brooks, Kanika Madan, Moksh Jain, Maksym Korablyov, Cheng-Hao Liu, Sarath Chandar, Nikolay Malkin, Yoshua Bengio

Comments Structured Probabilistic Inference and Generative Modeling (SPIGM) workshop @ ICML 2023

Geometric Autoencoders -- What You See is What You Decode

Philipp Nazari, Sebastian Damrich, Fred A. Hamprecht

Comments 24 pages, ICML 2023

DisasterResponseGPT: Large Language Models for Accelerated Plan of Action Development in Disaster Response Scenarios

Vinicius G. Goecks, Nicholas R. Waytowich

Comments Accepted at the Workshop on Challenges in Deployable Generative AI at International Conference on Machine Learning (ICML), Honolulu, Hawaii, USA. 2023

Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong Convexity

Risheng Liu, Yaohua Liu, Wei Yao, Shangzhi Zeng, Jin Zhang

Comments To be published in ICML 2023

UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers

Dachuan Shi, Chaofan Tao, Ying Jin, Zhendong Yang, Chun Yuan, Jiaqi Wang

Comments ICML 2023. Website: https://dachuanshi.com/UPop-Project

Algorithms for bounding contribution for histogram estimation under user-level privacy

Yuhan Liu, Ananda Theertha Suresh, Wennan Zhu, Peter Kairouz, Marco Gruteser

Comments 32 pages, ICML 2023

Improving Expert Predictions with Conformal Prediction

Eleni Straitouri, Lequn Wang, Nastaran Okati, Manuel Gomez Rodriguez

Comments Published at ICML 2023

Revisiting Precision and Recall Definition for Generative Model Evaluation

Loïc Simon, Ryan Webster, Julien Rabin

Comments ICML 2019

Journal ref PMLR 97:5799-5808, 2019

Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations

Yongyi Yang, Jacob Steinhardt, Wei Hu

Comments This paper has been accepted as a conference paper at ICML 2023

SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient

Max Ryabinin, Tim Dettmers, Michael Diskin, Alexander Borzunov

Comments Accepted to International Conference on Machine Learning (ICML) 2023. 25 pages, 8 figures