Decentralized Optimization

Ask about this topic

Overview

Decentralized optimization studies how networked agents can jointly minimize an objective or coordinate decisions while each uses local data and communicates with neighbors rather than relying on a central coordinator. Common approaches include gossip and consensus, decentralized stochastic gradient descent with gradient tracking, primal-dual and ADMM methods, and local updates paired with compressed or intermittent communication. These methods are tested in settings such as image and language-model training, online and bilevel learning, power systems, and multi-robot estimation. A central challenge is balancing communication cost, network topology, data heterogeneity, and robustness against noise or adversaries while retaining fast convergence and reliable solutions.

Latest papers

CardsList

60 papers15 papers in the last four weeks, up 150% on the four weeks before. 0.1% of all new papers.

  1. Revisiting Decentralized Online Convex Optimization with Compressed Communication

    Jul 2, 2026Hao Zhou, Xiaoyu Wang, Chang Yao +2Online Convex OptimizationFollow-the-Regularized-Leader

    School of Software Technology, Zhejiang University, Ningbo, China · State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China

  2. Decentralized Pose Graph Riemannian Optimization for Object-based Multi-Robot SLAM

    Jun 23, 2026Yixian Zhao, Yan Huang, Yang Xu +2Simultaneous Localization and MappingRiemannian Optimization

    College of Control Science and Engineering, Zhejiang University, Hangzhou, 310027, China · Division of Decision and Control Systems, School of EECS, KTH Royal Institute of Technology, Stockholm, SE-100 44, Sweden · Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, 201210, China

  3. DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity

    Jun 19, 2026Zhen Qin, Zhuqing Liu, Songtao Lu +2Bilevel OptimizationDecentralized Optimization

    Department of Electrical and Computer Engineering, The Ohio State University · Department of Computer Science and Engineering, University of North Texas · Department of Computer Science and Engineering, The Chinese University of Hong Kong

  4. Unifying Local Communications and Local Updates for LLM Pretraining

    Jun 9, 2026Pietro Cagnasso, Eugene Belilovsky, Edouard OyallonLanguage Model PretrainingCommunication-Efficient Distributed Training

    Concordia University · Mila · CNRS, Sorbonne University

  5. Improved Convergence Analysis of Topology Dependence in Decentralized SGD

    Jun 8, 2026Yuki Takezawa, Anastasia Koloskova, Sebastian U. StichOptimization Convergence AnalysisDecentralized Learning

    Toyota Motor Corporation · University of Zurich · CISPA Helmholtz Center for Information Security

  6. Accelerated Decentralized Stochastic Gradient Descent for Strongly Convex Optimization

    Jun 5, 2026Ming Sun, Kun YuanGradient DescentAccelerated Gradient Methods

    Center for Machine Learning Research Peking University

  7. Near-Optimal Decentralized Stochastic Convex Optimization over Networks

    Jun 3, 2026Nitai Kluger, Amit Attia, Tomer KorenStochastic Optimization ConvergenceAccelerated Gradient Methods

    Blavatnik School of Computer Science, Tel Aviv University · Google Research Tel Aviv

  8. S3^3LDBO: A Snapshot Single-Loop Algorithm for Decentralized Bilevel Optimization

    May 29, 2026Chao Yin, Youran Dong, Shiqian Ma +2Multi-Agent System OptimizationBilevel Optimization

    School of Mathematics, Hohai University, Nanjing, P. R. China · School of Mathematics, Nanjing University, Nanjing, P. R. China · Department of Computational Applied Mathematics and Operations Research, Rice University, Houston, USA

  9. Decentralized Parameter-Free Online Learning with Compressed Gossip

    May 27, 2026Tomas Ortega, Hamid JafarkhaniOnline Convex OptimizationDecentralized Learning

    Center for Pervasive Communications & Computing and EECS Department, University of California, Irvine, Irvine, CA 92697 USA

  10. FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning

    May 21, 2026Rachid HedjamFederated Learning AggregationNon-IID Federated Learning

    Department of Computer Science Bishop’s University Sherbrooke, Qc, Canada

  11. Distributed Direct Preference Optimization

    May 20, 2026Zhanhong JiangDirect Preference OptimizationNon-IID Federated Learning

    Translational AI Center, Iowa State University, Ames, USA.

  12. Efficient Gradient Methods for Distributed Saddle Problems

    May 18, 2026Ruichen Luo, Anton Rodomanov, Sebastian U. StichDistributed OptimizationDecentralized Optimization

    Institute of Science and Technology Austria · CISPA Helmholtz Center

  13. Unveiling High-Probability Generalization in Decentralized SGD

    May 11, 2026Jiahuan Wang, Ping Luo, Ziqing Wen +2Algorithmic StabilityDecentralized Learning

    College of Computer Science and Technology National University of Defense Technology Changsha, Hunan 410073, China

  14. ADKO: Agentic Decentralized Knowledge Optimization

    May 8, 2026Lucas Nerone Rillo, Zhanhong Jiang, Nastaran Saadati +4Multi-Agent System OptimizationAI Agents for Scientific Discovery

    Iowa State University · New York University

  15. \mathsf{VISTA}: Decentralized Machine Learning in Adversary Dominated Environments

    May 8, 2026Hanzaleh Akbari Nodehi, Parsa Moradi, Soheil Mohajer +1Mechanism DesignByzantine-Robust Federated Learning

    University of Minnesota

  16. Decentralized Time-Varying Optimization for Streaming Data via Temporal Weighting

    May 7, 2026Muhammad Faraz Ul Abrar, Nicolò Michelusi, Erik G. LarssonDecentralized Optimization

    School of Electrical, Computer and Energy Engineering, Arizona State University · Department of Electrical Engineering (ISY), Linköping University

  17. Stability and Generalization for Decentralized Markov SGD

    May 3, 2026Jiahuan Wang, Ziqing Wen, Ping Luo +2Algorithmic StabilityDecentralized Optimization

    National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, 410073, China

  18. High-Probability Convergence in Decentralized Stochastic Optimization with Gradient Tracking

    Apr 30, 2026Aleksandar Armacki, Haoyuan Cai, Ali H. SayedConvergence AnalysisStochastic Optimization Convergence

    Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland

  19. Accelerating Optimization and Machine Learning through Decentralization

    Apr 21, 2026Ziqin Chen, Zuang Wang, Yongqiang WangDistributed OptimizationDecentralized Learning

    Clemson University

  20. LoDAdaC: a unified local training-based decentralized framework with adaptive gradients and compressed communication

    Apr 11, 2026Wei Liu, Anweshit Panda, Ujwal Pandey +5Decentralized OptimizationCommunication-Efficient Distributed Training

    Department of Mathematical Sciences, Rensselaer Polytechnic Institute · Department of Computer Science, Rensselaer Polytechnic Institute · IBM T. J. Watson Research Center +1

  21. Convergence of Byzantine-Resilient Gradient Tracking via Probabilistic Edge Dropout

    Apr 1, 2026Amirhossein Dezhboro, Fateme Maleki, Arman Adibi +2Decentralized OptimizationStochastic Gradient Descent

    Department of Systems Engineering, Stevens Institute of Technology, Hoboken, NJ 07030. · Department of Industrial and Systems Engineering, Rutgers University, Piscataway, NJ 08854. · School of Computer and Cyber Sciences, Augusta University, Augusta, GA 30912. +1

  22. On Gossip Algorithms for Machine Learning with Pairwise Objectives

    Mar 25, 2026Igor Colin, Aurélien Bellet, Stephan Clémençon +1U-StatisticsDecentralized Optimization

    LTCI, S2A, IP Paris · LTCI, Télécom Paris, Institut Polytechnique de Paris · PREMEDICAL +4

  23. Stability and Generalization of Push-Sum Based Decentralized Optimization over Directed Graphs

    Feb 24, 2026Yifei Liang, Yan Sun, Xiaochun Cao +1Decentralized OptimizationDecentralized Learning

    School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen, Guangdong 518107, China · The University of Sydney, Sydney, NSW 2006, Australia

  24. Adaptive Decentralized Composite Optimization via Three-Operator Splitting

    Feb 19, 2026Xiaokai Chen, Ilya Kuruzov, Gesualdo ScutariDecentralized OptimizationNonsmooth Convex Optimization

    Edwardson School of Industrial Engineering, Purdue University, West Lafayette, IN 47906 USA

  25. Decentralized SGD with Controlled Disagreement Finds Flatter Minima

    Feb 2, 2026Zesen Wang, Mikael JohanssonDecentralized LearningFlat Minima

    Division of Decision and Control Systems KTH Royal Institute of Technology

  26. Fast and Efficient Asynchronous Gossip Algorithm for Robust and Non-Smooth Convex Decentralized Learning

    Jan 28, 2026Anna van Elst, Olivier Fercoq, Igor Colin +1Decentralized LearningNonsmooth Convex Optimization

    LTCI, Télécom Paris, Institut Polytechnique de Paris

  27. Distributed Dynamic Associative Memory via Online Convex Optimization

    Nov 28, 2025Bowen Wang, Matteo Zecchin, Osvaldo SimeoneOnline Convex OptimizationAssociative Memory

    Department of Engineering, King’s College London, London WC2R 2LS, U.K. · Communication Systems Department, EURECOM, 06904 Sophia Antipolis, France · Institute for Intelligent Networked Systems (INSI) at Northeastern University London, London E1 8PH, U.K.

  28. Game-theoretic Regulated Decentralized Coordination for Airspace Sector Overload Mitigation

    Nov 14, 2025Jaehan Im, Daniel Delahaye, David Fridovich-Keil +1Multi-Agent CoordinationAir Traffic Management

    The University of Texas at Austin, 110 Inner Campus Drive, Austin, 78712, Texas, United States · École Nationale de lAviation Civile, 7 Avenue Édouard Belin, CS 54005, Toulouse Cedex 4, 31055, France

  29. Decentralized Projection-free Online Upper-Linearizable Optimization with Applications to DR-Submodular Optimization

    Jan 30, 2025Yiyang Lu, Mohammad Pedramfar, Vaneet AggarwalSubmodular OptimizationOnline Convex Optimization

    Purdue University, West Lafayette, IN, USA · Mila - Quebec AI Institute/McGill University, Montreal, QC, Canada

  30. LOOP-MAC: Learning-Based Multi-Agent Coordination with Guaranteed Local Feasibility in a Virtual Power Plant

    Oct 27, 2023Meiyi Li, Lucas Ruda, Javad MohammadiMulti-Agent CoordinationPower Systems