Evolution Strategies
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Depth over Fidelity in Fixed-Budget Noisy Evolution Strategies
Announce Type: new Abstract: 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...
Gradient-Free Training of Spiking Neural Networks via Low-Rank Evolution Strategies
Announce Type: new Abstract: Spiking Neural Networks (SNNs) offer compelling energy efficiency on neuromorphic hardware, yet their training remains challenging because the discrete spike threshold is non-differentiable. Surrogate-gradient methods sidestep this by approximating the derivative, but they impose backpropagation infrastructure that is incompatible with on-chip learning. Evolution Strategies (\es) are a natural gradient-free alternative, yet their computational cost scales with...
Scalable Interference Graph Learning for Low-Latency Wi-Fi Networks using Hashing-based Evolution Strategy
arXiv:2502.03300v3 Announce Type: replace-cross Abstract: Wi-Fi 7 introduces the restricted target wake time (RTWT) mechanism, which is vital for Industrial IoT (IIoT) applications requiring periodic, reliable, and low-latency communication. RTWT enables deterministic channel access by assigning scheduled transmission slots to stations (STAs), minimizing contention and interference. However, determining efficient RTWT slot assignments remains challenging in dense networks, where conventional...
Dual-Chassis Strategy for Bridging Adaptive Evolution and Rational Design for Synthetic Biology
Genome streamlining and pathway refactoring are powerful strategies for constructing controllable microbial chassis for both fundamental studies and applications. While rational design benefits from reduced genetic complexity, adaptive laboratory evolution (ALE) thrives on metabolic redundancy, creating a mismatch between optimal hosts for design and evolution. Here, we introduce a dual chassis framework (DUET) in which rational pathway construction and adaptive evolution are first carried...
Distinguishing Photoacoustic and Photothermal Neuron Stimulation Through Quantitative Mapping Spatiotemporal Field Evolution
Neuromodulation is a rapidly advancing strategy for modulating brain function and treating neurological disorders, yet the mechanisms of optical neural stimulation remain incompletely understood. A central challenge is that photoacoustic (PA) and photothermal (PT) effects are typically generated simultaneously and evolve on overlapping spatial and temporal scales, making their contributions to neuronal activation difficult to distinguish. Here, we overcome this limitation by integrating two...
From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution
arXiv:2604.15097v2 Announce Type: replace Abstract: This beta technical report asks how reusable experience should be represented so that it can function as effective test-time control and as a substrate for iterative evolution. We study this question in 4.590 controlled trials across 45 scientific code-solving scenarios. We find that documentation-oriented Skill packages provide unstable control: their useful signal is sparse, and expanding a compact experience object into a fuller...
Quantitative Performance Analysis of Stopping Criteria for CMA-ES
Announce Type: new Abstract: Covariance matrix adaptation evolution strategy (CMA-ES) is a state-of-the-art black-box optimization algorithm. In general, CMA-ES uses a portfolio of multiple stopping criteria to automatically determine when to stop the search. This mechanism aims to avoid unnecessary consumption of the function evaluation budget during stagnation.
Exploring cooperation mechanisms via reinforcement learning in network common-pool resource games
arXiv:2606.05867v1 Announce Type: new Abstract: Sustaining cooperation in resource-constrained populations requires allocation mechanisms that balance individual incentives, resource sustainability, and distributional fairness. This paper proposes a network common-pool resource game in which individuals are embedded in complex networks, participate in multiple overlapping local resource pools, and face endogenous resource constraints during strategy evolution. Within this framework, we first...
Exploring cooperation mechanisms via reinforcement learning in network common-pool resource games
arXiv:2606.05867v1 Announce Type: cross Abstract: Sustaining cooperation in resource-constrained populations requires allocation mechanisms that balance individual incentives, resource sustainability, and distributional fairness. This paper proposes a network common-pool resource game in which individuals are embedded in complex networks, participate in multiple overlapping local resource pools, and face endogenous resource constraints during strategy evolution. Within this framework, we...
On the Generalization Gap in Self-Evolving Language Model Reasoning
new Abstract: Recent work suggests that large language models (LLMs) can improve through self-evolution (SE), using supervision signals generated by the model itself. In this work, we ask: under a strict closed-loop setup, where the self-evolution algorithm has access only to an unlabeled prompt set and a base model, how close can internally generated supervision come to oracle-supervised training? We analyze four representative strategies in a unified offline self-evolution framework:...