Random Minibatch Subgradient Algorithms for Convex Problems with Functional Constraints

Angelia Nedić, Ion Necoara

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

In this paper we consider non-smooth convex optimization problems with (possibly) infinite intersection of constraints. In contrast to the classical approach, where the constraints are usually represented as intersection of simple sets, which are easy to project onto, in this paper we consider that each constraint set is given as the level set of a convex but not necessarily differentiable function. For these settings we propose subgradient iterative algorithms with random minibatch feasibility updates. At each iteration, our algorithms take a subgradient step aimed at only minimizing the objective function and then a subsequent subgradient step minimizing the feasibility violation of the observed minibatch of constraints. The feasibility updates are performed based on either parallel or sequential random observations of several constraint components. We analyze the convergence behavior of the proposed algorithms for the case when the objective function is strongly convex and with bounded subgradients, while the functional constraints are endowed with a bounded first-order black-box oracle. For a diminishing stepsize, we prove sublinear convergence rates for the expected distances of the weighted averages of the iterates from the constraint set, as well as for the expected suboptimality of the function values along the weighted averages. Our convergence rates are known to be optimal for subgradient methods on this class of problems. Moreover, the rates depend explicitly on the minibatch size and show when minibatching helps a subgradient scheme with random feasibility updates.

Original languageEnglish (US)
Pages (from-to)801-833
Number of pages33
JournalApplied Mathematics and Optimization
Volume80
Issue number3
DOIs
StatePublished - Dec 1 2019

Keywords

  • Convergence rates
  • Convex minimization
  • Functional constraints
  • Random minibatch projection algorithms
  • Subgradient algorithms

ASJC Scopus subject areas

  • Control and Optimization
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Random Minibatch Subgradient Algorithms for Convex Problems with Functional Constraints'. Together they form a unique fingerprint.

Cite this