AI Paper Atlas

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

Certified Machine Unlearning Under High Dimensional Regime

Haolin Zou, Arnab Auddy, Yongchan Kwon, Kamiar Rahnama Rad, Arian Maleki

JMLR 2025 · Learning theory and algorithms › Prediction and decision losses · approach: Data attribution and recourse

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 two Newton steps instead of one (ablation)Newton-step certified unlearning, ridge logistic regression · Ridge logistic regression, m=1approximation error scaling in n: n^-0.5 -> n^-1.5Improved
use two Newton steps instead of one so less noise is needed for certification (ablation)Certified Newton unlearning plus Laplace noise · Ridge logistic regression, loss difference to exact unlearned modelloss error after noiseImproved
compare against Guo et al. 2019 single-step methodtwo-step Newton · Ridge logistic regression, single deletion (Figure 1)loss alignment with exact unlearningImproved
apply to sparse real bag-of-words data (IMDB)Newton unlearning theory · IMDB ridge logistic regressionerror scaling in mNo clear effect

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