Loading [MathJax]/extensions/MathZoom.js
A Unified PAC-Bayesian Framework for Machine Unlearning via Information Risk Minimization | IEEE Conference Publication | IEEE Xplore

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-trai...Show More

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.
Date of Conference: 25-28 October 2021
Date Added to IEEE Xplore: 15 November 2021
ISBN Information:
Print on Demand(PoD) ISSN: 1551-2541
Conference Location: Gold Coast, Australia

Funding Agency:


References

References is not available for this document.