Blind Random Search with Noisy Measurements: Almost Sure Convergence and Convergence Rates

arXiv:2610.33302v1 Announce Type: new Abstract: Blind random search is a simple global optimization method that only requires the value of the loss function, without needing gradient information or an explicit loss model. However, its classical formulation assumes that the loss evaluation is noise-free, which limits its direct application to practical problems with noisy measurements. We extend blind random search by combining a vanishing acceptance threshold with the running average of noisy loss measurements. Under the stated assumptions, we prove that the proposed algorithm converges almost surely to the global minimizer. We further analyze the rate at which the loss at the current estimate approaches the minimum loss. For low-dimensional cases, we obtain an almost sure asymptotic upper bound on the difference between the two, and for high-dimensional cases, we prove that this difference, suitably scaled, has an exact Weibull limiting distribution.

You are being forwarded in 6s — stay on this page