A Unified PAC-Bayesian Framework for Machine Unlearning via Information Risk Minimization

Sharu Theresa Jose, Osvaldo Simeone

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publication2021 IEEE 31st International Workshop on Machine Learning for Signal Processing, MLSP 2021
PublisherIEEE Computer Society
ISBN (Electronic)9781728163383
DOIs
StatePublished - 2021
Externally publishedYes
Event31st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2021 - Gold Coast, Australia
Duration: Oct 25 2021Oct 28 2021

Publication series

NameIEEE International Workshop on Machine Learning for Signal Processing, MLSP
Volume2021-October
ISSN (Print)2161-0363
ISSN (Electronic)2161-0371

Conference

Conference31st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2021
Country/TerritoryAustralia
CityGold Coast
Period10/25/2110/28/21

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Signal Processing

Keywords

  • free energy minimization
  • Machine unlearning
  • PAC-Bayesian bounds

Fingerprint

Dive into the research topics of 'A Unified PAC-Bayesian Framework for Machine Unlearning via Information Risk Minimization'. Together they form a unique fingerprint.

Cite this