Descent-to-delete: gradient-based methods for machine unlearning

MaRDI QIDQ7028610zbMATH OpenFDO

Authors Seth Neel, Aaron Roth, Saeed Sharifi-Malvajerdi

Publication date 11 February 2025

Full work available at URL https://proceedings.mlr.press/v132/neel21a.html

Mathematics Subject Classification ID

Statistical aspects of big data and data science (62R07) Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• Concentrated differential privacy: simplifications, extensions, and lower bounds
• Differential privacy under continual observation
• scientific article; zbMATH DE number 5485439 (Why is no real title available?)
• Random sampling with a reservoir
• The algorithmic foundations of differential privacy
• Theory of Cryptography

Cited in

(2)

• Efficient knowledge deletion from trained models through layer-wise partial machine unlearning
• The measure of deception: an analysis of data forging in machine unlearning

This page was built for publication: Descent-to-delete: gradient-based methods for machine unlearning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7028610)