Skip to main navigation Skip to search Skip to main content

Distributed Learning with Convex SUM-of -Non-Convex Objective

  • Northwestern Polytechnical University Xian
  • Université Côte d'Azur

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Recent research works have shown that some classical optimization methods originally designed for dealing with convex problems can demonstrate similar properties when applied to non-convex scenar-ios, where the problems are both locally and globally non-convex. This has led to the widespread development of distributed strategies for non-convex problems. When the sum of the local non-convex costs remains (strongly) convex and the individual local costs are smooth, it indicates a specific scenario that has notable applications and can benefit from existing solving methods. In this paper, drawing inspiration from the efficiency and stability of diffusion adaptation, we explore the minimization of a strongly convex sum of non-convex local costs. Specifically, we provide an analysis to demonstrate the convergence behavior of the network. Simulations are conducted to validate our theory.

Original languageEnglish
Title of host publication2023 IEEE 9th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages36-40
Number of pages5
ISBN (Electronic)9798350344523
DOIs
StatePublished - 2023
Event9th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2023 - Herradura, Costa Rica
Duration: 10 Dec 2023 → 13 Dec 2023

Publication series

Name2023 IEEE 9th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2023

Conference

Conference9th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2023
Country/TerritoryCosta Rica
CityHerradura
Period10/12/23 → 13/12/23

Keywords

  • Stochastic optimization
  • diffusion adaptation
  • non-convex cost

Fingerprint

Dive into the research topics of 'Distributed Learning with Convex SUM-of -Non-Convex Objective'. Together they form a unique fingerprint.

Cite this