{"ID":2887902,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.00495","arxiv_id":"2508.00495","title":"A linesearch-based derivative-free method for noisy black-box problems","abstract":"In this work we consider unconstrained optimization problems. The objective function is known through a zeroth order stochastic oracle that gives an estimate of the true objective function. To solve these problems, we propose a derivative-free algorithm based on extrapolation techniques. Under reasonable assumptions we are able to prove convergence properties for the proposed algorithms. Furthermore, we also give a worst-case complexity result stating that the total number of iterations where the expected value of the norm of the objective function gradient is above a prefixed $ε\u003e0$ is ${\\cal O}(n^2ε^{-2}/β^2)$ in the worst case.","short_abstract":"In this work we consider unconstrained optimization problems. The objective function is known through a zeroth order stochastic oracle that gives an estimate of the true objective function. To solve these problems, we propose a derivative-free algorithm based on extrapolation techniques. Under reasonable assumptions we...","url_abs":"https://arxiv.org/abs/2508.00495","url_pdf":"https://arxiv.org/pdf/2508.00495v1","authors":"[\"Alberto De Santis\",\"Giampaolo Liuzzi\",\"Stefano Lucidi\"]","published":"2025-08-01T10:17:48Z","proceeding":"math.OC","tasks":"[\"math.OC\"]","methods":"[]","has_code":false}