MUSO: achieving exact machine unlearning in over-parameterized regimes

DOI10.1007/S10994-025-06806-0MaRDI QIDQ6903664zbMATH OpenFDO

Authors Ruikai Yang, Mingzhen He, Zhenghao He, Youmei Qiu, Xiaolin Huang

Publication date 10 November 2025

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S10994-025-06806-0

zbMATH Keywords

machine unlearningover-parameterized modelrandom featuresrelabeling method

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• Characterizations of an Empirical Influence Function for Detecting Influential Cases in Regression
• CUR matrix decompositions for improved data analysis
• Finding structure with randomness: probabilistic algorithms for constructing approximate matrix decompositions
• Machine unlearning: linear filtration for logit-based classifiers
• Optimal survival trees
• Random Fourier features for asymmetric kernels
• Relative-Error CUR Matrix Decompositions
• The interpolation phase transition in neural networks: memorization and generalization under lazy training
• Two models of double descent for weak features

This page was built for publication: MUSO: achieving exact machine unlearning in over-parameterized regimes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6903664)