Adaptive two-points zero-order accelerated methods for stochastic convex optimization problems
Year: 2026
Type: preprint
Abstract: We study stochastic convex optimization, where each sampled function can be evaluated at two arbitrary points. Our accelerated method chooses step sizes, batch sizes and smoothing radii from function values. A forward difference between smoothing scales controls the radius; we account for changes in the smoothed objective. Under the stated regularity and second-moment assumptions, exact function evaluations give \begin{multline*} \mathbb{E}\bigl[f(x_N)-f(x^\star)\bigr] \le \widetilde{O}\biggl( \frac{\sqrt{d}\,M_2 D}{\sqrt{T}} +\min\biggl( \frac{L D^2}{N^2},\; \frac{d^{1/4} M D}{N}+\frac{\sqrt{d}\,M D^2}{γ_{\max} N^2} \biggr)\biggr). \end{multline*} Here $N,T,d,D$ denote the numbers of optimization steps and paired evaluations, the dimension and a feasible-set diameter bound, respectively. Evaluations are available within Euclidean distance $γ_{\max}$ of the feasible set. For the population objective $f(x)=\mathbb{E}_ξ F(x,ξ)$, $M$ satisfies $|f(x)-f(y)|\le M\|x-y\|_2$, and $M_2$ satisfies $\mathbb{E}_ξ\|\nabla F(x,ξ)\|_2^2\le M_2^2$ for sample weak gradients in the interior of the evaluation domain. The method requires no $L,M,M_2$, where $L$ is a Lipschitz constant of $\nabla f$; set $L=+\infty$ without smoothness. The method uses exactly $2T$ values in $3N$ sequential sampling rounds with predetermined batches, or $5N$ with batches chosen from observations. An extension selects a search radius without a supplied distance bound. Fixed radius parameters can leave nonvanishing error; suitable choices depending on the budgets yield convergence.
Source: arXiv (Cornell University)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7221829606