Saved in:
Bibliographic Details
Main Authors: Avetisyan, Arutyun, Dvinskikh, Darina, Gasnikov, Alexander, Temlyakov, Vladimir, Tupitsa, Nazarii, Turdakov, Denis
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.16875
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917503099207680
author Avetisyan, Arutyun
Dvinskikh, Darina
Gasnikov, Alexander
Temlyakov, Vladimir
Tupitsa, Nazarii
Turdakov, Denis
author_facet Avetisyan, Arutyun
Dvinskikh, Darina
Gasnikov, Alexander
Temlyakov, Vladimir
Tupitsa, Nazarii
Turdakov, Denis
contents This paper aims to motivate stochastic optimization problems from a statistical perspective and a statistical learning perspective, where the goal is to maximize the log-likelihood or minimize the population risk. We briefly describe the two main approaches: offline (Monte Carlo / Sample Average Approximation) and online (Stochastic Approximation) approaches -- to solve the expectation minimization problems.
format Preprint
id arxiv_https___arxiv_org_abs_2605_16875
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Stochastic Optimization and Data Science
Avetisyan, Arutyun
Dvinskikh, Darina
Gasnikov, Alexander
Temlyakov, Vladimir
Tupitsa, Nazarii
Turdakov, Denis
Optimization and Control
This paper aims to motivate stochastic optimization problems from a statistical perspective and a statistical learning perspective, where the goal is to maximize the log-likelihood or minimize the population risk. We briefly describe the two main approaches: offline (Monte Carlo / Sample Average Approximation) and online (Stochastic Approximation) approaches -- to solve the expectation minimization problems.
title Stochastic Optimization and Data Science
topic Optimization and Control
url https://arxiv.org/abs/2605.16875