ResearchTrend.AI
  • Communities
  • Connect sessions
  • AI calendar
  • Organizations
  • Contact Sales
Papers
Communities
Social Events
Terms and Conditions
Pricing
Contact Sales
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2012.03503
225
10
v1v2v3v4v5 (latest)

Block majorization-minimization with diminishing radius for constrained nonconvex optimization

7 December 2020
Hanbaek Lyu
Yuchen Li
ArXiv (abs)PDFHTML
Abstract

Block majorization-minimization (BMM) is a simple iterative algorithm for nonconvex constrained optimization that sequentially minimizes majorizing surrogates of the objective function in each block coordinate while the other coordinates are held fixed. BMM entails a large class of optimization algorithms such as block coordinate descent and its proximal-point variant, expectation-minimization, and block projected gradient descent. We establish that for general constrained nonconvex optimization, BMM with strongly convex surrogates can produce an ϵ\epsilonϵ-stationary point within O(ϵ−2(log⁡ϵ−1)2)O(\epsilon^{-2}(\log \epsilon^{-1})^{2})O(ϵ−2(logϵ−1)2) iterations and asymptotically converges to the set of stationary points. Furthermore, we propose a trust-region variant of BMM that can handle surrogates that are only convex and still obtain the same iteration complexity and asymptotic stationarity. These results hold robustly even when the convex sub-problems are inexactly solved as long as the optimality gaps are summable. As an application, we show that a regularized version of the celebrated multiplicative update algorithm for nonnegative matrix factorization by Lee and Seung has iteration complexity of O(ϵ−2(log⁡ϵ−1)2)O(\epsilon^{-2}(\log \epsilon^{-1})^{2})O(ϵ−2(logϵ−1)2). The same result holds for a wide class of regularized nonnegative tensor decomposition algorithms as well as the classical block projected gradient descent algorithm. These theoretical results are validated through various numerical experiments.

View on arXiv
Comments on this paper