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. 1605.07747
22
45

NESTT: A Nonconvex Primal-Dual Splitting Method for Distributed and Stochastic Optimization

25 May 2016
Davood Hajinezhad
Mingyi Hong
T. Zhao
Zhaoran Wang
ArXivPDFHTML
Abstract

We study a stochastic and distributed algorithm for nonconvex problems whose objective consists of a sum of NNN nonconvex Li/NL_i/NLi​/N-smooth functions, plus a nonsmooth regularizer. The proposed NonconvEx primal-dual SpliTTing (NESTT) algorithm splits the problem into NNN subproblems, and utilizes an augmented Lagrangian based primal-dual scheme to solve it in a distributed and stochastic manner. With a special non-uniform sampling, a version of NESTT achieves ϵ\epsilonϵ-stationary solution using O((∑i=1NLi/N)2/ϵ)\mathcal{O}((\sum_{i=1}^N\sqrt{L_i/N})^2/\epsilon)O((∑i=1N​Li​/N​)2/ϵ) gradient evaluations, which can be up to O(N)\mathcal{O}(N)O(N) times better than the (proximal) gradient descent methods. It also achieves Q-linear convergence rate for nonconvex ℓ1\ell_1ℓ1​ penalized quadratic problems with polyhedral constraints. Further, we reveal a fundamental connection between primal-dual based methods and a few primal only methods such as IAG/SAG/SAGA.

View on arXiv
Comments on this paper