Accelerated Bregman proximal gradient methods for relatively smooth convex optimization

Filip Hanzely, Peter Richtarik, Lin Xiao

Research output: Contribution to journalArticlepeer-review

17 Scopus citations

Abstract

We consider the problem of minimizing the sum of two convex functions: one is differentiable and relatively smooth with respect to a reference convex function, and the other can be nondifferentiable but simple to optimize. We investigate a triangle scaling property of the Bregman distance generated by the reference convex function and present accelerated Bregman proximal gradient (ABPG) methods that attain an O(k-γ) convergence rate, where γ∈ (0 , 2] is the triangle scaling exponent (TSE) of the Bregman distance. For the Euclidean distance, we have γ= 2 and recover the convergence rate of Nesterov’s accelerated gradient methods. For non-Euclidean Bregman distances, the TSE can be much smaller (say γ≤ 1), but we show that a relaxed definition of intrinsic TSE is always equal to 2. We exploit the intrinsic TSE to develop adaptive ABPG methods that converge much faster in practice. Although theoretical guarantees on a fast convergence rate seem to be out of reach in general, our methods obtain empirical O(k- 2) rates in numerical experiments on several applications and provide posterior numerical certificates for the fast rates.
Original languageEnglish (US)
JournalComputational Optimization and Applications
DOIs
StatePublished - Apr 7 2021

Bibliographical note

KAUST Repository Item: Exported on 2021-04-22
Acknowledgements: We thank Haihao Lu, Robert Freund and Yurii Nesterov for helpful conversations. We are also grateful to the anonymous referees whose comments helped improving the clarity of the paper. Peter Richtárik acknowledges the support of the KAUST Baseline Research Funding Scheme.

ASJC Scopus subject areas

  • Control and Optimization
  • Computational Mathematics
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Accelerated Bregman proximal gradient methods for relatively smooth convex optimization'. Together they form a unique fingerprint.

Cite this