ICML - arXivDaily 期刊&会议

2310.04400 2024-06-07 cs.LG cs.IR

On the Embedding Collapse when Scaling up Recommendation Models

Xingzhuo Guo, Junwei Pan, Ximei Wang, Baixu Chen, Jie Jiang, Mingsheng Long

Comments ICML 2024 Accepted

2310.02442 2024-06-07 cs.LG

GenCO: Generating Diverse Designs with Combinatorial Constraints

Aaron Ferber, Arman Zharmagambetov, Taoan Huang, Bistra Dilkina, Yuandong Tian

Comments Accepted to ICML 2024

2310.00165 2024-06-07 cs.LG cs.CV

SCoRe: Submodular Combinatorial Representation Learning

Anay Majee, Suraj Kothawade, Krishnateja Killamsetty, Rishabh Iyer

Comments Accepted to ICML 2024

2307.16422 2024-06-07 math.ST cs.LG stat.ML stat.TH

Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution

Elen Vardanyan, Sona Hunanyan, Tigran Galstyan, Arshak Minasyan, Arnak Dalalyan

Comments ICML 2024

2306.04815 2024-06-07 cs.LG math.OC stat.ML

Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning

Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin

Comments ICML 2024

2406.03494 2024-06-06 cs.LG cs.NA math.NA stat.ML

Solving Poisson Equations using Neural Walk-on-Spheres

Hong Chul Nam, Julius Berner, Anima Anandkumar

Comments Accepted at ICML 2024

2406.03485 2024-06-06 cs.LG cs.AI

Highway Value Iteration Networks

Yuhui Wang, Weida Li, Francesco Faccio, Qingyuan Wu, Jürgen Schmidhuber

Comments ICML 2024

2406.03422 2024-06-06 cs.GT

Causal Inference from Competing Treatments

Ana-Andreea Stoica, Vivian Y. Nastl, Moritz Hardt

Comments 37 pages, 3 figures, accepted at ICML'24

2406.03421 2024-06-06 cs.CV

Post-hoc Part-prototype Networks

Andong Tan, Fengtao Zhou, Hao Chen

Comments ICML 2024

2402.12535 2024-06-06 cs.LG hep-ex

Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics

Siqi Miao, Zhiyuan Lu, Mia Liu, Javier Duarte, Pan Li

Comments Accepted to ICML 2024 (Oral)

2402.11168 2024-06-06 cs.LG cs.AI

Trust Regions for Explanations via Black-Box Probabilistic Certification

Amit Dhurandhar, Swagatam Haldar, Dennis Wei, Karthikeyan Natesan Ramamurthy

Comments Accepted to ICML 2024

2310.00344 2024-06-06 cs.LG

HarmonyDream: Task Harmonization Inside World Models

Haoyu Ma, Jialong Wu, Ningya Feng, Chenjun Xiao, Dong Li, Jianye Hao, Jianmin Wang, Mingsheng Long

Comments ICML 2024. Code is available at https://github.com/thuml/HarmonyDream

2406.03288 2024-06-06 cs.LG stat.ML

Embarrassingly Parallel GFlowNets

Tiago da Silva, Luiz Max Carvalho, Amauri Souza, Samuel Kaski, Diego Mesquita

Comments Accepted to ICML 2024

2406.03255 2024-06-06 cs.LG

On the Maximal Local Disparity of Fairness-Aware Classifiers

Jinqiu Jin, Haoxuan Li, Fuli Feng

Journal ref ICML 2024

2406.03234 2024-06-06 cs.LG cs.AI

Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning

Inwoo Hwang, Yunhyeok Kwak, Suhyung Choi, Byoung-Tak Zhang, Sanghack Lee

Comments ICML 2024

2406.03171 2024-06-06 stat.ML cs.LG

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization

Yihang Chen, Fanghui Liu, Taiji Suzuki, Volkan Cevher

Comments ICML 2024

2406.03164 2024-06-06 cs.LG

Topological Neural Networks go Persistent, Equivariant, and Continuous

Yogesh Verma, Amauri H Souza, Vikas Garg

Comments Accepted to ICML 2024

2406.03152 2024-06-06 cs.DS cs.LG

Dynamic Spectral Clustering with Provable Approximation Guarantee

Steinar Laenen, He Sun

Comments This work is accepted at the 41st International Conference on Machine Learning (ICML'24)

2406.03148 2024-06-06 cs.LG

Aligning Transformers with Weisfeiler-Leman

Luis Müller, Christopher Morris

Comments Accepted at ICML 2024

2406.03141 2024-06-06 q-bio.BM cs.LG

Floating Anchor Diffusion Model for Multi-motif Scaffolding

Ke Liu, Weian Mao, Shuaike Shen, Xiaoran Jiao, Zheng Sun, Hao Chen, Chunhua Shen

Comments ICML 2024

2406.03057 2024-06-06 cs.LG stat.ML

BWS: Best Window Selection Based on Sample Scores for Data Pruning across Broad Ranges

Hoyong Choi, Nohyun Ki, Hye Won Chung

Comments ICML 2024

2406.03006 2024-06-06 quant-ph cs.DS cs.LG math.OC

Quantum Algorithms and Lower Bounds for Finite-Sum Optimization

Yexin Zhang, Chenyi Zhang, Cong Fang, Liwei Wang, Tongyang Li

Comments 27 pages. To appear in the Forty-first International Conference on Machine Learning International Conference on Machine Learning (ICML 2024)

2406.02915 2024-06-06 cs.CV cs.LG

Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models

Jinhao Li, Haopeng Li, Sarah Erfani, Lei Feng, James Bailey, Feng Liu

Comments 22 pages, 16 figures, published to ICML 2024

2406.02910 2024-06-06 cs.DS

High-Dimensional Geometric Streaming for Nearly Low Rank Data

Hossein Esfandiari, Vahab Mirrokni, Praneeth Kacham, David P. Woodruff, Peilin Zhong

Comments ICML 2024

2406.02873 2024-06-06 stat.ML cs.LG

Prediction-powered Generalization of Causal Inferences

Ilker Demirel, Ahmed Alaa, Anthony Philippakis, David Sontag

Comments International Conference on Machine Learning (ICML), 2024

2406.02862 2024-06-06 cs.CV

Rethinking Guidance Information to Utilize Unlabeled Samples:A Label Encoding Perspective

Yulong Zhang, Yuan Yao, Shuhao Chen, Pengrong Jin, Yu Zhang, Jian Jin, Jiangang Lu

Comments Accepted to ICML 2024

2406.02790 2024-06-06 cs.LG cs.CY

Building Socially-Equitable Public Models

Yejia Liu, Jianyi Yang, Pengfei Li, Tongxin Li, Shaolei Ren

Comments Accepted by the ICML 2024

2406.02644 2024-06-06 cs.CR cs.AI cs.DS

Differentially private exact recovery for stochastic block models

Dung Nguyen, Anil Vullikanti

Comments Accepted by ICML 2024

2406.02309 2024-06-06 cs.LG

Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing

Youwei Shu, Xi Xiao, Derui Wang, Yuxin Cao, Siji Chen, Jason Xue, Linyi Li, Bo Li

Comments ICML 2024 Poster

2406.00645 2024-06-06 cs.LG cs.AI cs.CV

FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning

Yuwei Fu, Haichao Zhang, Di Wu, Wei Xu, Benoit Boulet

Comments ICML 2024