ICML "distribution shift" Papers

15 papers found

Cross-domain Open-world Discovery

Shuo Wen, Maria Brbic

ICML 2024poster

Domain-wise Data Acquisition to Improve Performance under Distribution Shift

Yue He, Dongbai Li, Pengfei Tian et al.

ICML 2024poster

Ensemble Pruning for Out-of-distribution Generalization

Fengchun Qiao, Xi Peng

ICML 2024poster

FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction

Zhonghang Li, Lianghao Xia, Yong Xu et al.

ICML 2024oral

Improving Generalization in Offline Reinforcement Learning via Adversarial Data Splitting

Da Wang, Lin Li, Wei Wei et al.

ICML 2024poster

Multi-Source Conformal Inference Under Distribution Shift

Yi Liu, Alexander Levis, Sharon-Lise Normand et al.

ICML 2024poster

OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift

Lin Li, Yifei Wang, Chawin Sitawarin et al.

ICML 2024poster

Performative Prediction with Bandit Feedback: Learning through Reparameterization

Yatong Chen, Wei Tang, Chien-Ju Ho et al.

ICML 2024poster

Prompting is a Double-Edged Sword: Improving Worst-Group Robustness of Foundation Models

Amrith Setlur, Saurabh Garg, Virginia Smith et al.

ICML 2024poster

Pseudo-Calibration: Improving Predictive Uncertainty Estimation in Unsupervised Domain Adaptation

Dapeng Hu, Jian Liang, Xinchao Wang et al.

ICML 2024poster

Reducing Balancing Error for Causal Inference via Optimal Transport

Yuguang Yan, Hao Zhou, Zeqin Yang et al.

ICML 2024poster

SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual Datasets

Shenghua Wan, Ziyuan Chen, Le Gan et al.

ICML 2024poster

TabLog: Test-Time Adaptation for Tabular Data Using Logic Rules

Weijieying Ren, Xiaoting Li, Huiyuan Chen et al.

ICML 2024poster

Test-Time Model Adaptation with Only Forward Passes

Shuaicheng Niu, Chunyan Miao, Guohao Chen et al.

ICML 2024poster

Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution Learnability

Sepanta Zeighami, Cyrus Shahabi

ICML 2024poster