AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Noisy Pairwise-Comparison Random Search for Smooth Nonconvex Optimization

Taha EL BAKKALI EL KADI, Rayane Bouftini, Qiuyi Zhang, Omar Saadi

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
lower intrinsic dimension of the fine-tuning taskNCRS, MeZO, RSGF · GLUE MRPC/QQP LM fine-tuningiterations to reach SGD accuracyImproved
use NCRS instead of RSGFNCRS · GLUE MRPC/QQP LM fine-tuningiterations to reach SGD accuracyImproved
use MeZO instead of NCRSMeZO · GLUE MRPC/QQP LM fine-tuningiterations to reach SGD accuracyMixed
increase model size with sufficient pretrainingzeroth-order methods · GLUE MRPC/QQP LM fine-tuningiterationsImproved
use NCRS with confidence-weighted vote for preference RLNCRS · DM Control Suite preference RLground truth rewardNo 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