mlsanityData to 14 Oct 2026

DualFL: A Duality-based Federated Learning Algorithm with Communication Acceleration in the General Convex Regime

arXiv 2305.10294 ↗First posted 17 May 2023cs.LG math.OCcited by 2

Not on the map. Why?

Abstract (arXiv)

We propose a new training algorithm, named DualFL (Dualized Federated Learning), for solving distributed optimization problems in federated learning. DualFL achieves communication acceleration for very general convex cost functions, thereby providing a solution to an open theoretical problem in federated learning concerning cost functions that may not be smooth nor strongly convex. We provide a detailed analysis for the local iteration complexity of DualFL to ensure the overall computational efficiency of DualFL. Furthermore, we introduce a completely new approach for the convergence analysis of federated learning based on a dual formulation. This new technique enables concise and elegant analysis, which contrasts the complex calculations used in existing literature on convergence of federated learning algorithms.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 32 of its 58 references that are in the map. First posted on arXiv 17 May 2023.

Builds on

32 of 58 references.

References · 32

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2021Convex optimizationcited by 2,515
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  5. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  6. 2019Tighter Theory for Local SGD on Identical and Heterogeneous Datacited by 266
  7. 2020FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Datacited by 144
  8. 2022Generalized Federated Learning via Sharpness Aware Minimizationcited by 144
  9. 2022ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!cited by 134
  10. 2021Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradientscited by 123
  11. 2020FedSplit: An algorithmic framework for fast federated optimizationcited by 108
  12. 2020Local SGD: Unified Theory and New Efficient Methodscited by 88
20 more
  1. 2021FedCM: Federated Learning with Client-level Momentumcited by 77
  2. 2015Communication Complexity of Distributed Convex Learning and Optimizationcited by 60
  3. 2018How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGDcited by 57
  4. 2020Federated Composite Optimizationcited by 49
  5. 2015Incremental Gradient, Subgradient, and Proximal Methods for Convex Optimization: A Surveycited by 45
  6. 2015An optimal randomized incremental gradient methodcited by 33
  7. 2022Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learningcited by 33
  8. 2021The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communicationcited by 31
  9. 2021FedDR -- Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimizationcited by 29
  10. 2022RandProx: Primal-Dual Optimization Algorithms with Randomized Proximal Updatescited by 28
  11. 2022Can 5th Generation Local Training Methods Support Client Sampling? Yes!cited by 22
  12. 2013On the Complexity Analysis of Randomized Block-Coordinate Descent Methodscited by 21
  13. 2022Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with Inexact Proxcited by 19
  14. 2018Optimizing the Efficiency of First-Order Methods for Decreasing the Gradient of Smooth Convex Functionscited by 14
  15. 2017Backtracking strategies for accelerated descent methods with smooth composite objectivescited by 7
  16. 2017Adaptive Restart of the Optimized Gradient Method for Convex Optimizationcited by 6
  17. 2020Principled Analyses and Design of First-Order Methods with Inexact Proximal Operatorscited by 5
  18. 2019Additive Schwarz Methods for Convex Optimization as Gradient Methodscited by 4
  19. 2021Scaled, inexact and adaptive generalized FISTA for strongly convex optimizationcited by 4
  20. 2021Fast Gradient Methods for Uniformly Convex and Weakly Smooth Problemscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2026Fisher-Informed Parameterwise Aggregation for Federated Learning with Heterogeneous Datacited by 1
  2. 2024Accelerating Distributed Optimization: A Primal-Dual Perspective on Local Stepscited by 0