AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

ECPv2: Fast, Efficient, and Scalable Global Optimization of Lipschitz Functions

Fares Fourati, Mohamed-Slim Alouini, Vaneet Aggarwal

AAAI 2026 · Optimization › Nonconvex and smooth optimization · approach: Adaptive first-order convex methods · 2 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
add Worst-m memory (compare candidates against only the m worst points) (ablation)ECP · 12 benchmark functionsacceptance-test cost: roughly 4--5x reductionImproved
use small m in {8,16,32,64,128} instead of full memory (ablation)ECPv2 · Himmelblau, Holder and ten other functionsfinal best valueNo clear effect
increase m toward full memory (ablation)ECPv2 · benchmark functionsperformance and runtimeNo clear effect
add adaptive lower bound to avoid empty acceptance regions (ablation)ECP · low evaluation budgetsruntime: roughly 2x fasterImproved
combine random projection with Worst-m rule (ablation)ECPv2 · Rosenbrock d=500runtimeImproved
replace ECP with ECPv2 on high-dimensional problemsECP · Rosenbrock d=500, Powell d=1000convergence speed and score: roughly 2x fasterImproved
increase beta from 0.05 to 5 in projection dimension bound (ablation)ECPv2 random projection · 100 points in R^1000, delta=0.5distance preservationImproved

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