AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Gradientless Descent: High-Dimensional Zeroth-Order Optimization

ICLR 2020 · Optimization › Nonconvex and smooth optimization · approach: Complexity of nonconvex first-order methods · 37 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Project the HalfCheetah linear-policy state to 200 dimensionsGLD with a linear policy · HalfCheetah-v1maximum reward: 4064 -> 4342Helped
Use GLD-Fast rather than GLD-SearchGLD · BBOB benchmarksoptimality gapHelped
Use GLD-Fast rather than ARSzeroth-order optimization · high-dimensional quadratic objectivesoptimality gapHelped
Apply a monotone transformation to the objectiveGLD · transformed quadratic objectivesconvergenceNo clear effect
Over-approximate the condition number supplied to GLD-FastGLD-Fast · quadratic objectivesoptimality gapHelped
Underestimate the condition number supplied to GLD-FastGLD-Fast · quadratic objectivesconvergenceNo 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