Skip to results
MLSift
← Feed
Theory & OptimizationZero-order optimization2607.12938

Sharp Optimal Algorithm for Derivative-Free Stochastic Convex Optimization in One Dimension

Alexandra Carpentier, Chloé Rouyer, Alexandre Tsybakov, Arya Akhavan

math.OC stat.ML

Abstract

Stochastic convex optimization is a classical problem with well-understood guarantees under first-order feedback. In contrast, for zero-order optimization with noisy function evaluations, a logarithmic gap has persisted between known upper bounds and the $Ω(1/\sqrt{T})$ lower bound, even in the one-dimensional case. In this work, we study the problem of minimizing a convex function $f : [0,1] \to [0,1]$ using a zero-order oracle with subGaussian noise. We propose a computationally efficient algorithm that achieves the optimal $O(1/\sqrt{T})$ convergence rate, matching the lower bound. The result closes the existing gap in one dimension, providing the first sharp rate guarantee in this setting.

Topics

Classified with taxonomy v2 on Wed, 2 Sept 2026.

The PDF is 1–3 MB. Open it in your browser's viewer, or load it here.

Open PDF