@inproceedings{adea331b6bee4b349a6ba998aab9f654,
title = "A unified PAC-Bayesian framework for machine unlearning via information risk minimization",
abstract = "Machine unlearning refers to mechanisms that can remove the influence of a subset of training data upon request from a trained model without incurring the cost of re-training from scratch. This paper develops a unified PAC-Bayesian framework for machine unlearning that recovers the two recent design principles - variational unlearning [1] and forgetting Lagrangian [2] as information risk minimization problems [3]. Accordingly, both criteria can be interpreted as PAC-Bayesian upper bounds on the test loss of the unlearned model that take the form of free energy metrics.",
keywords = "Machine unlearning, PAC-Bayesian bounds, free energy minimization",
author = "Sharu Jose and Osvaldo Simeone",
year = "2021",
month = nov,
day = "15",
doi = "10.1109/MLSP52302.2021.9596170",
language = "English",
isbn = "9781665411844 (PoD)",
series = "Machine learning for signal processing ",
publisher = "IEEE",
booktitle = "2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)",
}