ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1901.09344
17
29

Stochastic Approximation of Smooth and Strongly Convex Functions: Beyond the O(1/T)O(1/T)O(1/T) Convergence Rate

27 January 2019
Lijun Zhang
Zhi-Hua Zhou
ArXivPDFHTML
Abstract

Stochastic approximation (SA) is a classical approach for stochastic convex optimization. Previous studies have demonstrated that the convergence rate of SA can be improved by introducing either smoothness or strong convexity condition. In this paper, we make use of smoothness and strong convexity simultaneously to boost the convergence rate. Let λ\lambdaλ be the modulus of strong convexity, κ\kappaκ be the condition number, F∗F_*F∗​ be the minimal risk, and α>1\alpha>1α>1 be some small constant. First, we demonstrate that, in expectation, an O(1/[λTα]+κF∗/T)O(1/[\lambda T^\alpha] + \kappa F_*/T)O(1/[λTα]+κF∗​/T) risk bound is attainable when T=Ω(κα)T = \Omega(\kappa^\alpha)T=Ω(κα). Thus, when F∗F_*F∗​ is small, the convergence rate could be faster than O(1/[λT])O(1/[\lambda T])O(1/[λT]) and approaches O(1/[λTα])O(1/[\lambda T^\alpha])O(1/[λTα]) in the ideal case. Second, to further benefit from small risk, we show that, in expectation, an O(1/2T/κ+F∗)O(1/2^{T/\kappa}+F_*)O(1/2T/κ+F∗​) risk bound is achievable. Thus, the excess risk reduces exponentially until reaching O(F∗)O(F_*)O(F∗​), and if F∗=0F_*=0F∗​=0, we obtain a global linear convergence. Finally, we emphasize that our proof is constructive and each risk bound is equipped with an efficient stochastic algorithm attaining that bound.

View on arXiv
Comments on this paper