Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models

Conference proceeding

Anshuman Chhabra, Bo Li, Jian Chen, Prasant Mohapatra and Hongfu Liu

Proceedings of Machine Learning Research - International Conference on Machine Learning, ICML 2025, Vol.267, pp.10334-10353

2025

Metrics

1 Record Views

Title: Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models
Creators: Anshuman Chhabra - University of South Florida
Bo Li - Tsinghua University
Jian Chen - Tsinghua University
Prasant Mohapatra - University of South Florida
Hongfu Liu - Brandeis University, Waltham, MA, United States
Publication Details: Proceedings of Machine Learning Research - International Conference on Machine Learning, ICML 2025, Vol.267, pp.10334-10353
Grant note: 72171131; 72133002 / National Natural Science Foundation of China (http://data.elsevier.com/vocabulary/SciValFunders/501100001809) National Natural Science Foundation of China (http://data.elsevier.com/vocabulary/SciValFunders/501100001809) USF CSE department faculty startup fund
Identifiers: 9924558804501921
Academic Unit: Michtom School of Computer Science; Benjamin and Mae Volen National Center for Complex Systems
Language: English
Resource Type: Conference proceeding