A unified PAC-Bayesian framework for machine unlearning via information risk minimization
Machine Learning
2021-06-02 v1 Information Theory
Signal Processing
math.IT
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 (Nguyen et.al., 2020) and forgetting Lagrangian (Golatkar et.al., 2020) - as information risk minimization problems (Zhang,2006). 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.
Cite
@article{arxiv.2106.00265,
title = {A unified PAC-Bayesian framework for machine unlearning via information risk minimization},
author = {Sharu Theresa Jose and Osvaldo Simeone},
journal= {arXiv preprint arXiv:2106.00265},
year = {2021}
}
Comments
Under Review