AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Finding Differentially Private Second Order Stationary Points in Stochastic Minimax Optimization

Difei Xu, Youming Tao, Meng Ding, Chenglin Fan, Di Wang

ICML 2026 · Optimization › Nonconvex and smooth optimization · approach: Nonconvex minimax and constrained methods · 0 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 DP-RGDA instead of Sto-SPIDER on explicit value functionDP-SOSP baselines · synthetic matrix sensingPhi(x_399): 13.7046 -> 0.9119Improved
use DP-RGDA instead of Ada-DP-SPIDERDP-SOSP baselines · synthetic matrix sensingPhi(x_399): 8.0751 -> 0.9119Improved
use DP-RGDA instead of Sto-SPIDERDP-SOSP baselines · synthetic matrix sensinggradient norm: 3.4505 -> 0.4251Improved
use DP-RGDA instead of Ada-DP-SPIDERDP-SOSP baselines · synthetic matrix sensinggradient norm: 2.2753 -> 0.4251Improved
use DP-RGDA instead of Sto-SPIDERDP-SOSP baselines · synthetic matrix sensinglambda_min: -2.1862e-1 -> -4.8504e-2Improved
use PrivateDiff instead of DP-RGDA (first-order DP minimax baseline)DP-RGDA · synthetic matrix sensingPhi(x_399): 0.9119 -> 0.6546Hurt
use PrivateDiff instead of DP-RGDADP-RGDA · synthetic matrix sensinglambda_min: -4.8504e-2 vs -4.3622e-2No 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