[Paper] Depth over Fidelity in Fixed-Budget Noisy Evolution Strategies

Published: (June 4, 2026 at 06:35 AM EDT)
1 min read
Source: arXiv

Source: arXiv - 2606.06555v1

Overview

Noisy evolution strategies under fixed evaluation budgets face a depth-fidelity trade-off: spending evaluations to denoise intra-generation rankings reduces the number of distribution updates the optimizer can execute. We argue for depth over fidelity and propose probabilistic elite membership (PEM), which replaces hard rank-based weights in evolution strategies with conditional expected rank weights that integrate over ranking uncertainty. PEM preserves the conditional mean update while reducing conditional update dispersion, a Rao-Blackwellization of the noisy rank-based step. We instantiate PEM via residual bootstrapping (RB-PEM) with capped per-generation overhead, complemented by an adaptive probe-and-switch mechanism for low-noise regimes. Across the COCO bbob-noisy suite and external tasks including RL policy search and hyperparameter optimization, RB-PEM achieves consistent gains in high-misranking, budget-constrained settings.

Key Contributions

This paper presents research in the following areas:

  • cs.NE
  • cs.LG

Methodology

Please refer to the full paper for detailed methodology.

Practical Implications

This research contributes to the advancement of cs.NE.

Authors

  • Sichen Wang
  • Zhipeng Lu

Paper Information

  • arXiv ID: 2606.06555v1
  • Categories: cs.NE, cs.LG
  • Published: June 4, 2026
  • PDF: Download PDF
0 views
Back to Blog

Related posts

Read more »