Statistical Query Algorithms for Mean Vector Estimation and Stochastic Convex Optimization

Vitaly Feldman, Cristóbal Andrés Guzmán Paredes, Santosh Vempala

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Stochastic convex optimization, by which the objective is the expectation of a random convex function, is an important and widely used method with numerous applications in machine learning, statistics, operations research, and other areas. We study the complexity of stochastic convex optimization given only statistical query (SQ) access to the objective function. We show that well-known and popular first-order iterative methods can be implemented using only statistical queries. For many cases of interest, we derive nearly matching upper and lower bounds on the estimation (sample) complexity, including linear optimization in the most general setting. We then present several consequences for machine learning, differential privacy, and proving concrete lower bounds on the power of convex optimization–based methods. The key ingredient of our work is SQ algorithms and lower bounds for estimating the mean vector of a distribution over vectors supported on a convex body in R<jats:sup>d</jats:sup>. This natural problem has not been previously studied, and we show that our solutions can be used to get substantially improved SQ versions of Perceptron and other online algorithms for learning halfspaces.
Original languageEnglish
Pages (from-to)912-945
Number of pages34
JournalMathematics of operations research
Volume46
Issue number3
Early online date8 Mar 2021
DOIs
Publication statusPublished - Aug 2021

Fingerprint

Dive into the research topics of 'Statistical Query Algorithms for Mean Vector Estimation and Stochastic Convex Optimization'. Together they form a unique fingerprint.

Cite this