AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Algorithms that Approximate Data Removal: New Results and Limitations

Vinith Menon Suriyakumar, Ashia Camage Wilson

NeurIPS 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Active learning and subset selection · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use IJ instead of retraining from scratchunlearning with l2 logistic regression · MNIST 3 vs 8runtime: 2611xImproved
use IJ instead of Algorithm TA (Hessian inverted once, not per request)unlearning with l2 logistic regression · MNIST 3 vs 8runtime: 2045xImproved
use IJ instead of Algorithm TAunlearning, test accuracy · MNIST 3 vs 8test accuracyNo clear effect
adaptive instead of random delete requestsIJ · MNIST 3 vs 8test accuracyNo clear effect
use IJ (proximal Newton) instead of retraining with l1 regularizerunlearning with l1 logistic regression · Warfarin dosingruntime: 30xImproved
use IJ instead of retraining, l1 regularizerunlearning with l1 logistic regression · Warfarin dosingtest accuracyMixed
use IJ instead of retraining on non-convex DP feature extractorunlearning · SVHN 3 vs 8runtime: 15036xImproved
use IJ instead of TA on non-convex DP feature extractorunlearning · SVHN 3 vs 8runtime: 17xImproved
use IJ on non-convex setting as deletions increaseunlearning · SVHN 3 vs 8test accuracyNo clear effect
select lambda by cross-validation before unlearningapproximate unlearning guarantees · theory counterexampleunlearning guaranteeHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy