An accelerated variant achieving the expected convergence rate of $\sigma_1/\sqrt{T}+\sigma_2/T^2+1/T^{7/2})$ is developed, matching the known lower bounds of Agafonov et al. (2024) in all three terms.
A. Agafonov, Аслан Нажмудинович Ашабоков, D. Kamzolov et al.· 0 citations
We consider distributed stochastic convex optimization with a fixed budget of $N$ independent samples split among $m$ workers. Sample average approximation reduces the problem to a regularized finite-sum problem whose local Hessians are statistically similar. This allows the Hessian of the local objective at the server...
Yury A. Sokolov, Maxim Mashtaler, A. Gasnikov et al.· 0 citations
We study entropy-regularized linear programs with sparse affine constraints and compare two exact dual representations induced by whether a redundant normalization constraint is retained or eliminated. Eliminating it yields a partially separable sum-exp dual with sparse affine factors but unbounded curvature. Our main...
I. Podlipnova, Maxim Mashtaler, A. Agafonov et al.· 0 citations
This work derives a finite-sample comparison of clipped and unclipped Polyak-Ruppert averaged SGD under finite conditional $p$-th moments, and gives explicit accuracy and confidence conditions under which, for $p>2$, the Gaussian term dominates the unclipped deviation bound, so clipping need not improve its leading ord...
A. Suvorikova, E. Gladin, D. Dvinskikh et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.