mlsanityData to 14 Oct 2026

Accelerated Methods with Complexity Separation Under Data Similarity for Federated Learning Problems

arXiv 2601.08614 ↗First posted 13 Jan 2026math.OC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Heterogeneity within data distribution poses a challenge in many modern federated learning tasks. We formalize it as an optimization problem involving a computationally heavy composite under data similarity. By employing different sets of assumptions, we present several approaches to develop communication-efficient methods. An optimal algorithm is proposed for the convex case. The constructed theory is validated through a series of experiments across various problems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 47 references that are in the map. First posted on arXiv 13 Jan 2026.

Builds on

31 of 47 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2019A Survey on Distributed Machine Learningcited by 188
  4. 2013Communication Efficient Distributed Optimization using an Approximate Newton-type Methodcited by 132
  5. 2016Relatively-Smooth Convex Optimization by First-Order Methods, and Applicationscited by 108
  6. 2019Unified Optimal Analysis of the (Stochastic) Gradient Methodcited by 82
  7. 2015Communication Complexity of Distributed Convex Learning and Optimizationcited by 60
  8. 2015A Universal Catalyst for First-Order Optimizationcited by 54
  9. 2018On the Ineffectiveness of Variance Reduced Optimization for Deep Learningcited by 48
  10. 2020Statistically Preconditioned Accelerated Gradient Method for Distributed Optimizationcited by 30
  11. 2019On Convergence of Distributed Approximate Newton Methods: Globalization, Sharper Bounds and Beyondcited by 18
  12. 2022Faster federated optimization under second-order similaritycited by 18
19 more
  1. 2021Acceleration in Distributed Optimization under Similaritycited by 17
  2. 2018Katyusha X: Practical Momentum Method for Stochastic Sum-of-Nonconvex Optimizationcited by 15
  3. 2014Gradient Sliding for Composite Optimizationcited by 14
  4. 2021On Accelerated Methods for Saddle-Point Problems with Composite Structurecited by 13
  5. 2023Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysiscited by 11
  6. 2022Compression and Data Similarity: Combination of Two Techniques for Communication-Efficient Solving of Distributed Variational Inequalitiescited by 8
  7. 2016Accelerated gradient sliding for structured convex optimizationcited by 7
  8. 2023Two Losses Are Better Than One: Faster Optimization Using a Cheaper Proxycited by 7
  9. 2023Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalitiescited by 7
  10. 2024Stabilized Proximal-Point Methods for Federated Optimizationcited by 7
  11. 2019Derivative-Free Method For Composite Optimization With Applications To Decentralized Distributed Optimizationcited by 4
  12. 2020Oracle Complexity Separation in Convex Optimizationcited by 4
  13. 2022Adaptive Third-Order Methods for Composite Convex Optimizationcited by 4
  14. 2025Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysiscited by 4
  15. 2020On the Optimal Combination of Tensor Optimization Methodscited by 3
  16. 2021Mirror-prox sliding methods for solving a class of monotone variational inequalitiescited by 2
  17. 2024Accelerated Methods with Compressed Communications for Distributed Optimization Problems under Data Similaritycited by 2
  18. 2022The Mirror-Prox Sliding Method for Non-smooth decentralized saddle-point problemscited by 1
  19. 2024Extragradient Sliding for Composite Non-Monotone Variational Inequalitiescited by 1

Built on by

Not cited yet.