Work

Stochastic Optimization and Data Science

Year: 2026

Type: preprint

Abstract: 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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2605.16875

Authors: Avetisyan, Arutyun, Dvinskikh, Darina, Gasnikov, Alexander, Temlyakov, Vladimir, Tupitsa, Nazarii, Turdakov, Denis

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7161680208

Cites: 33

Cited by: 1

Related to: 10