Incremental constraint projection methods for variational inequalities
Name
Bertsekas_Incremental constraint.pdf
Size
492.37 KB
Format
Adobe PDF
Checksum (MD5)
ea656ad869ff36e322e8f02335007e54
Author(s)
Wang, Mengdi
Bertsekas, Dimitri P.
Date Issued
May 2014
Journal
Mathematical Programming
Publisher
Springer-Verlag
Citation
Wang, Mengdi, and Dimitri P. Bertsekas. “Incremental Constraint Projection Methods for Variational Inequalities.” Math. Program. 150, no. 2 (May 17, 2014): 321–363.
Version
Original manuscript
Abstract
We consider the solution of strongly monotone variational inequalities of the form \(F(x^*)'(x-x^*)\ge 0\), for all \(x\in X\). We focus on special structures that lend themselves to sampling, such as when \(X\) is the intersection of a large number of sets, and/or \(F\) is an expected value or is the sum of a large number of component functions. We propose new methods that combine elements of incremental constraint projection and stochastic gradient. These methods are suitable for problems involving large-scale data, as well as problems with certain online or distributed structures. We analyze the convergence and the rate of convergence of these methods with various types of sampling schemes, and we establish a substantial rate of convergence advantage for random sampling over cyclic sampling.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/s10107-014-0769-x
