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. 2409.19279
16
0

Distributed Optimization via Energy Conservation Laws in Dilated Coordinates

28 September 2024
Mayank Baranwal
Kushal Chakrabarti
ArXivPDFHTML
Abstract

Optimizing problems in a distributed manner is critical for systems involving multiple agents with private data. Despite substantial interest, a unified method for analyzing the convergence rates of distributed optimization algorithms is lacking. This paper introduces an energy conservation approach for analyzing continuous-time dynamical systems in dilated coordinates. Instead of directly analyzing dynamics in the original coordinate system, we establish a conserved quantity, akin to physical energy, in the dilated coordinate system. Consequently, convergence rates can be explicitly expressed in terms of the inverse time-dilation factor. Leveraging this generalized approach, we formulate a novel second-order distributed accelerated gradient flow with a convergence rate of O(1/t2−ϵ)O\left(1/t^{2-\epsilon}\right)O(1/t2−ϵ) in time ttt for ϵ>0\epsilon>0ϵ>0. We then employ a semi second-order symplectic Euler discretization to derive a rate-matching algorithm with a convergence rate of O(1/k2−ϵ)O\left(1/k^{2-\epsilon}\right)O(1/k2−ϵ) in kkk iterations. To the best of our knowledge, this represents the most favorable convergence rate for any distributed optimization algorithm designed for smooth convex optimization. Its accelerated convergence behavior is benchmarked against various state-of-the-art distributed optimization algorithms on practical, large-scale problems.

View on arXiv
Comments on this paper