AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Differentially Private Stochastic Optimization: New Results in Convex and Non-Convex Settings

Raef Bassily, Cristóbal A Guzmán, Michael Menart

NeurIPS 2021 · Optimization › Nonconvex and smooth optimization · approach: Stochastic convex optimization complexity · 6 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
Approximate Moreau envelope of generalized linear loss to smooth it, then use DP-SCO smooth algorithm in l2DP-SCO for non-smooth GLL · l2 settingrunning timeImproved
Use noisy Frank-Wolfe with Rademacher generalization bounds for GLL in l1DP-SCO non-smooth GLL · l1 settingexcess riskImproved
Use variance-reduced stochastic Frank-Wolfe with round scheduling for non-convex smooth lossesprivate non-convex SO · l1 settingstationarity rateImproved
Linear-time l2 algorithm versus prior superlinear unconstrained methodprivate non-convex SO · l2 settingstationarity rateMixed

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