Stochastic Reformulations of Linear Systems: Algorithms and Convergence Theory

Peter Richtarik, Martin Takãč

Research output: Contribution to journalArticlepeer-review

7 Scopus citations

Abstract

We develop a family of reformulations of an arbitrary consistent linear system into a stochastic problem. The reformulations are governed by two user-defined parameters: a positive definite matrix defining a norm, and an arbitrary discrete or continuous distribution over random matrices. Our reformulation has several equivalent interpretations, allowing for researchers from various communities to leverage their domain-specific insights. In particular, our reformulation can be equivalently seen as a stochastic optimization problem, stochastic linear system, stochastic fixed point problem, and a probabilistic intersection problem. We prove sufficient, and necessary and sufficient, conditions for the reformulation to be exact. Further, we propose and analyze three stochastic algorithms for solving the reformulated problem-basic, parallel, and accelerated methods-with global linear convergence rates. The rates can be interpreted as condition numbers of a matrix which depends on the system matrix and on the reformulation parameters. This gives rise to a new phenomenon which we call stochastic preconditioning and which refers to the problem of finding parameters (matrix and distribution) leading to a sufficiently small condition number. Our basic method can be equivalently interpreted as stochastic gradient descent, stochastic Newton method, stochastic proximal point method, stochastic fixed point method, and stochastic projection method, with fixed stepsize (relaxation parameter), applied to the reformulations.
Original languageEnglish (US)
Pages (from-to)487-524
Number of pages38
JournalSIAM Journal on Matrix Analysis and Applications
Volume41
Issue number2
DOIs
StatePublished - Apr 21 2020

Fingerprint

Dive into the research topics of 'Stochastic Reformulations of Linear Systems: Algorithms and Convergence Theory'. Together they form a unique fingerprint.

Cite this