Papers › Descent-to-Delete: Gradient-Based Methods for Machine Unlearning

Descent-to-Delete: Gradient-Based Methods for Machine Unlearning

6 Jul 2020arXiv:2007.02923archive 2025-07-28

Seth Neel, Aaron Roth, Saeed Sharifi-Malvajerdi

We study the data deletion problem for convex models. By leveraging techniques from convex optimization and reservoir sampling, we give the first data deletion algorithms that are able to handle an arbitrarily long sequence of adversarial updates while promising both per-deletion run-time and steady-state error that do not grow with the length of the update sequence. We also introduce several new conceptual distinctions: for example, we can ask that after a deletion, the entire state maintained by the optimization algorithm is statistically indistinguishable from the state that would have resulted had we retrained, or we can ask for the weaker condition that only the observable output is statistically indistinguishable from the observable output that would have resulted from retraining. We are able to give more efficient deletion algorithms under this weaker deletion criterion.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ChrisWaites/data-deletion mentioned on GitHubjaxnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready report
ChrisWaites/descent-to-delete mentioned on GitHubjaxnot reachable when probed 2026-09-16 — repositories for recent papers often appear after camera-ready report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Machine Unlearning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections