arXiv · 2609.12590
Tight Sampling Complexity with Stochastic Gradient Oracles in Fixed Dimensions
Abstract
We establish the stochastic-gradient query complexity of sampling smooth strongly log-concave distributions in every fixed dimension $d\geq1$. For $μ$-strongly convex, $L$-smooth potentials with unknown minimizers $x_f^\star$ in the ball $\mathbb{B}(0,μ^{-1/2})$, and unbiased gradient oracles with variance at most $σ^2$, the minimax worst-case expected query complexity is $Θ\left(\log(1+κ)+\frac{σ^2}{μ\varepsilon}\right)$, jointly optimal for the condition number $κ:=L/μ$, variance $σ^2\ge 0$, and TV accuracy $0<\varepsilon\leq 1/10$. In the noiseless setting $σ=0$, this tight complexity $Θ\left(\log(1+κ)\right)$ is independent of $\varepsilon$. Moreover, a gradient-only sampler generates an exact sample with ${O}(\log(1+κ))$ worst-case expected queries. Without previous ball $\mathbb{B}(0,μ^{-1/2})$, exact sampling from any initial point $x_0$ can be implemented with expected cost ${O}\left(\log(1+κ)+\log(1+\sqrtμ\|x_0-x_f^\star\|)\right)$, without knowing the initial distance. We also show that dependence on initial distance is generally unavoidable.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Weiming Ou, Xiao Wang. 2026-09-26. Tight Sampling Complexity with Stochastic Gradient Oracles in Fixed Dimensions. https://searcharxiv.com/abs/2609.12590
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.