AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Depth over Fidelity in Fixed-Budget Noisy Evolution Strategies

Sichen Wang, Zhipeng Lu

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Distributed LLM inference systems · 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 Probe-and-Switch instead of 10-fold resamplingCMA-ES · All COCO bbob-noisy + 6 external taskswin rate: 85.6%Improved
use Probe-and-Switch instead of 5-fold resamplingCMA-ES · All COCO bbob-noisy + 6 external taskswin rate: 79.3%Improved
use Probe-and-Switch instead of UH-CMA-ESCMA-ES · All COCO bbob-noisy + 6 external taskswin rate: 77.4%Improved
add Probe-and-Switch over vanilla CMA-ESCMA-ES · All COCO bbob-noisy + 6 external taskswin rate: 54.3%Improved
add probe-and-switch to RB-PEM (revert to CMA-ES in low-misranking regimes) (ablation)RB-PEM · All COCO bbob-noisy + 6 external taskswin rate: 58.1%Improved
add Probe-and-Switch vs CMA-ES, COCO d=10CMA-ES · COCO bbob-noisy d=10wins: 230/210No clear effect
add Probe-and-Switch vs CMA-ES, COCO d=40CMA-ES · COCO bbob-noisy d=40wins: 257/170Improved
add Probe-and-Switch vs CMA-ES on DigitsCMA-ES · Digitswins: 17/33Hurt
add Probe-and-Switch vs CMA-ES on LQRCMA-ES · LQRwins: 31/19Improved
use conservative threshold 0.22 instead of 0.12 (ablation)Probe-and-Switch · external tasks (HPO, Pendulum)regret reduction: tau 0.12 -> 0.22Mixed

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