mlsanityData to 14 Oct 2026

Federated Distributionally Robust Optimization with Non-Convex Objectives: Algorithm and Analysis

arXiv 2307.14364 ↗First posted 25 Jul 2023math.OC cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Distributionally Robust Optimization (DRO), which aims to find an optimal decision that minimizes the worst case cost over the ambiguity set of probability distribution, has been widely applied in diverse applications, e.g., network behavior analysis, risk management, etc. However, existing DRO techniques face three key challenges: 1) how to deal with the asynchronous updating in a distributed environment; 2) how to leverage the prior distribution effectively; 3) how to properly adjust the degree of robustness according to different scenarios. To this end, we propose an asynchronous distributed algorithm, named Asynchronous Single-looP alternatIve gRadient projEction (ASPIRE) algorithm with the itErative Active SEt method (EASE) to tackle the federated distributionally robust optimization (FDRO) problem. Furthermore, a new uncertainty set, i.e., constrained D-norm uncertainty set, is developed to effectively leverage the prior distribution and flexibly control the degree of robustness. Finally, our theoretical analysis elucidates that the proposed algorithm is guaranteed to converge and the iteration complexity is also analyzed. Extensive empirical studies on real-world datasets demonstrate that the proposed method can not only achieve fast convergence, and remain robust against data heterogeneity as well as malicious attacks, but also tradeoff robustness with performance.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 44 of its 119 references that are in the map. First posted on arXiv 25 Jul 2023.

Builds on

44 of 119 references.

References · 44

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2021Convex optimizationcited by 2,515
  4. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,150
  5. 2018How To Backdoor Federated Learningcited by 765
  6. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  7. 2019Agnostic Federated Learningcited by 456
  8. 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 360
  9. 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 335
  10. 2019On Gradient Descent Ascent for Nonconvex-Concave Minimax Problemscited by 270
  11. 2019A backdoor attack against LSTM-based text classification systemscited by 227
  12. 2016Distributionally Robust Stochastic Optimization with Wasserstein Distancecited by 185
32 more
  1. 2020Large-Scale Methods for Distributionally Robust Optimizationcited by 179
  2. 2019SCAFFOLD: Stochastic Controlled Averaging for Federated Learningcited by 175
  3. 2019Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learningcited by 170
  4. 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 125
  5. 2021Distributionally Robust Federated Averagingcited by 104
  6. 2019Wasserstein Adversarial Examples via Projected Sinkhorn Iterationscited by 89
  7. 2021Federated Reconstruction: Partially Local Federated Learningcited by 79
  8. 2019Distributionally Robust Optimization: A Reviewcited by 76
  9. 2020A Unified Single-loop Alternating Gradient Projection Algorithm for Nonconvex-Concave and Convex-Nonconcave Minimax Problemscited by 57
  10. 2019Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applicationscited by 55
  11. 2021Optimized Power Control Design for Over-the-Air Federated Edge Learningcited by 48
  12. 2020Advances in Asynchronous Parallel and Distributed Optimizationcited by 40
  13. 2022Federated Minimax Optimization: Improved Convergence Analyses and Algorithmscited by 37
  14. 2018Robust Optimization over Multiple Domainscited by 34
  15. 2019Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradientscited by 32
  16. 2021Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learningcited by 21
  17. 2022Scalable and Low-Latency Federated Learning with Cooperative Mobile Edge Networkingcited by 18
  18. 2015A Practical Guide to Robust Optimizationcited by 16
  19. 2020Stable Adversarial Learning under Distributional Shiftscited by 16
  20. 2021Bayesian Distributionally Robust Optimizationcited by 16
  21. 2022Distributed Distributionally Robust Optimization with Non-Convex Objectivescited by 14
  22. 2022Asynchronous Distributed Bilevel Optimizationcited by 13
  23. 2015Asynchronous Distributed ADMM for Large-Scale Optimization- Part I: Algorithm and Convergence Analysiscited by 10
  24. 2023Federated Minimax Optimization with Client Heterogeneitycited by 8
  25. 2021Derivative-free Alternating Projection Algorithms for General Nonconvex-Concave Minimax Problemscited by 7
  26. 2021Semi-asynchronous Hierarchical Federated Learning for Cooperative Intelligent Transportation Systemscited by 6
  27. 2022GBA: A Tuning-free Approach to Switch between Synchronous and Asynchronous Training for Recommendation Modelcited by 4
  28. 2013A cutting surface algorithm for semi-infinite convex programming with an application to moment robust optimizationcited by 3
  29. 2022Towards cost-effective and resource-aware aggregation at Edge for Federated Learningcited by 3
  30. 2020Robustness analytics to data heterogeneity in edge computingcited by 2
  31. 2021Federated Distributionally Robust Optimization for Phase Configuration of RISscited by 2
  32. 2018Chronos: A Unifying Optimization Framework for Speculative Execution of Deadline-critical MapReduce Jobscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024Group Distributionally Robust Dataset Distillation with Risk Minimizationcited by 10
  2. 2025Distributionally Robust Federated Learning with Outlier Resiliencecited by 1
  3. 2026LLM-Driven Multi-Turn Task-Oriented Dialogue Synthesis for Realistic Reasoningcited by 0
  4. 2026First-order Constrained Trilevel Optimization Over Distributed Networks for Robust Coreset Selectioncited by 0