Skip to content
  • enzuazua
  • Events Calendar
  • Jobs
cmc.deusto.eus
  • Home
  • About us
    • About DeustoCCM
    • Head of DeustoCCM
    • Team
    • Past Members
  • Research
    • Projects
    • ERC CoDeFeL
    • Computational Mathematics Research Group
    • DyCon Blog
    • DyCon Toolbox
    • Industrial & Social TransferenceContents related to the industrial and social transference aspects of the work in the Chair of Computational Mathematics.
  • Publications
    • Publications (All)
    • Publications by year
      • Publications 2025
      • Publications 2024
      • Publications 2023
      • Publications 2022
      • Publications 2021
      • Publications 2020
      • Publications 2019
      • Publications 2018
      • Publications 2017
      • Publications 2016
    • AcceptedAccepted to be released
    • SubmittedSubmitted publications
  • Activities
    • Events calendar
    • Seminars
    • Highlights
    • Our Latest
    • Courses
    • Past Events
    • enzuazua
    • Gallery
  • Jobs
  • Contact

A Multi-Objective Optimization framework for Decentralized Learning with coordination constraints

Roberto Morales, U. Biccari (2025) A Multi-Objective Optimization framework for Decentralized Learning with coordination constraints,

Abstract. This article introduces a generalized framework for Decentralized Learning formulated as a Multi-Objective Optimization problem, in which both distributed agents and a central coordinator contribute independent, potentially conflicting objectives over a shared model parameter space. Unlike traditional approaches that merge local losses under a common goal, our formulation explicitly incorporates coordinator-side criteria, enabling more flexible and structured training dynamics. To navigate the resulting trade-offs, we explore scalarization strategies, particularly weighted sums, to construct tractable surrogate problems. These yield solutions that are provably Pareto optimal under standard convexity and smoothness assumptions, while embedding global preferences directly into local updates. We propose a decentralized optimization algorithm with convergence guarantees, and demonstrate its empirical performance through simulations, highlighting the impact of the coordinator’s influence on local agent behavior. The proposed approach offers a principled and customizable strategy for balancing personalization, fairness, and coordination in decentralized learning systems.

arxiv: 2507.13983

  • Benasque XI Workshop-Summer School 2026: Partial differential equations, optimal design and numerics
  • The Mathematics of Scientific Machine Learning and Digital Twins
  • DeustoCCM Seminar: Research on Control Problems of Several Types of Infinite-Dimensional Systems
  • DeustoCCM Seminar: Developing Mathematical and Physical Tools for Multiscale Dynamical Systems. Applications to Neurophysiological Data
Copyright 2016 - 2025 DeustoCCM — cmc.deusto.eus. All rights reserved. Chair of Computational Mathematics, University of Deusto
Scroll to Top
  • Aviso Legal
  • Política de Privacidad
  • Política de Cookies
  • Configuración de Cookies
WE USE COOKIES ON THIS SITE TO ENHANCE USER EXPERIENCE. We also use analytics. By navigating any page you are giving your consent for us to set cookies.    more information
Privacidad