PulseAugur
LIVE 04:22:57
research · [3 sources] ·
0
research

New algorithms tackle black-box optimization with unreliable feedback

Researchers have developed a new adaptive optimization algorithm called POO (parallel optimistic optimization) designed to handle noisy functions with unknown smoothness. This algorithm aims to perform comparably to existing methods that require prior knowledge of function smoothness. POO is applicable to a broader range of functions, particularly those that are challenging to optimize, and its performance has been analyzed to show a minimal error gap compared to known algorithms. AI

Summary written by gemini-2.5-flash-lite from 3 sources. How we write summaries →

IMPACT Introduces a novel optimization technique that could improve the efficiency of training complex machine learning models.

RANK_REASON This is a research paper detailing a new algorithm for black-box optimization.

Read on arXiv stat.ML →

COVERAGE [3]

  1. arXiv cs.LG TIER_1 · Nicolas Samuel Blumer, Julien Martinelli, Samuel Kaski ·

    In-Context Black-Box Optimization with Unreliable Feedback

    arXiv:2605.06187v1 Announce Type: new Abstract: Black-box optimization in science and engineering often comes with side information: experts, simulators, pretrained predictors, or heuristics can suggest which candidates look promising. This information can accelerate search, but …

  2. arXiv stat.ML TIER_1 · Jean-Bastien Grill, Michal Valko, R\'emi Munos ·

    Black-box optimization of noisy functions with unknown smoothness

    arXiv:2605.02462v1 Announce Type: new Abstract: We study the problem of black-box optimization of a function f of any dimension, given function evaluations perturbed by noise. The function is assumed to be locally smooth around one of its global optima, but this smoothness is unk…

  3. arXiv stat.ML TIER_1 · Rémi Munos ·

    Black-box optimization of noisy functions with unknown smoothness

    We study the problem of black-box optimization of a function f of any dimension, given function evaluations perturbed by noise. The function is assumed to be locally smooth around one of its global optima, but this smoothness is unknown. Our contribution is an adaptive optimizati…