mlsanityData to 7 Oct 2026

Local Exact-Diffusion for Decentralized Optimization and Learning

arXiv 2302.00620 ↗First posted 1 Feb 2023math.OCcited by 24

Not on the map. Why?

Abstract (arXiv)

Distributed optimization methods with local updates have recently attracted a lot of attention due to their potential to reduce the communication cost of distributed methods. In these algorithms, a collection of nodes performs several local updates based on their local data, and then they communicate with each other to exchange estimate information. While there have been many studies on distributed local methods with centralized network connections, there has been less work on decentralized networks. In this work, we propose and investigate a locally updated decentralized method called Local Exact-Diffusion (LED). We establish the convergence of LED in both convex and nonconvex settings for the stochastic online setting. Our convergence rate improves over the rate of existing decentralized methods. When we specialize the network to the centralized case, we recover the state-of-the-art bound for centralized methods. We also link LED to several other independently studied distributed methods, including Scaffnew, FedGate, and VRL-SGD. Additionally, we numerically investigate the benefits of local updates for decentralized networks and demonstrate the effectiveness of the proposed method.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Feb 2023.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 5; 2025: 9; 2026: 5.

24 papers.

Sort:

  1. 2023Stochastic Controlled Averaging for Federated Learning with Communication Compressioncited by 100
  2. 2023Momentum Benefits Non-IID Federated Learning Simply and Provablycited by 37
  3. 2023Composite federated learning with heterogeneous datacited by 7
  4. 2024The Effectiveness of Local Updates for Decentralized Learning under Data Heterogeneitycited by 7
  5. 2024Hierarchical Federated Learning with Multi-Timescale Gradient Correctioncited by 7
  6. 2023Towards Understanding Generalization and Stability Gaps between Centralized and Decentralized Federated Learningcited by 3
  7. 2024Enhancing Privacy in Federated Learning through Local Trainingcited by 3
  8. 2025Communication-Efficient Stochastic Distributed Learningcited by 3
  9. 2025Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participationcited by 3
  10. 2023A Proximal Gradient Method With Probabilistic Multi-Gossip Communications for Decentralized Composite Optimizationcited by 2
  11. 2025Gradient Correction in Federated Learning with Adaptive Optimizationcited by 1
  12. 2025Jointly Computation- and Communication-Efficient Distributed Learningcited by 1
12 more
  1. 2025A Communication-Efficient Decentralized Actor-Critic Algorithmcited by 1
  2. 2026Communication-Efficient Distributed Learning with Differential Privacycited by 1
  3. 2024Accelerating Distributed Optimization: A Primal-Dual Perspective on Local Stepscited by 0
  4. 2024A Stochastic Approximation Approach for Efficient Decentralized Optimization on Random Networkscited by 0
  5. 2025Modular Distributed Nonconvex Learning with Error Feedbackcited by 0
  6. 2025Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentumcited by 0
  7. 2025Diffusion Learning with Partial Agent Participation and Local Updatescited by 0
  8. 2025Communication-Efficient Learning for Satellite Constellationscited by 0
  9. 2026Accelerating Decentralized Optimization via Overlapping Local Stepscited by 0
  10. 2026Local Updates in Distributed Optimization: Provable Acceleration and Topology Effectscited by 0
  11. 2026Local adapt-then-combine algorithms for distributed nonsmooth optimization: Achieving provable communication accelerationcited by 0
  12. 2026SPADE-DFL: Communication-Efficient Decentralized Federated Learning via Derivative-Free Linearized ADMMcited by 0