mlsanityData to 7 Oct 2026

Distributed Distributionally Robust Optimization with Non-Convex Objectives

arXiv 2210.07588 ↗First posted 14 Oct 2022cs.LG cs.AIcited by 14

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 distributed distributionally robust optimization (DDRO) 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 14 papers in the map (data through 7 Oct 2026). Builds on 29 of its 66 references that are in the map. First posted on arXiv 14 Oct 2022.

Builds on

29 of 66 references.

References · 29

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  3. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,140
  4. 2018How To Backdoor Federated Learningcited by 745
  5. 2019Agnostic Federated Learningcited by 451
  6. 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 358
  7. 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 334
  8. 2019On Gradient Descent Ascent for Nonconvex-Concave Minimax Problemscited by 266
  9. 2019A backdoor attack against LSTM-based text classification systemscited by 214
  10. 2016Distributionally Robust Stochastic Optimization with Wasserstein Distancecited by 182
  11. 2020Large-Scale Methods for Distributionally Robust Optimizationcited by 179
  12. 2019SCAFFOLD: Stochastic Controlled Averaging for Federated Learningcited by 174
17 more
  1. 2019Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learningcited by 169
  2. 2021Distributionally Robust Federated Averagingcited by 104
  3. 2021Federated Reconstruction: Partially Local Federated Learningcited by 78
  4. 2019Efficient Algorithms for Smooth Minimax Optimizationcited by 75
  5. 2020A Unified Single-loop Alternating Gradient Projection Algorithm for Nonconvex-Concave and Convex-Nonconcave Minimax Problemscited by 56
  6. 2019Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applicationscited by 55
  7. 2018On the Fenchel Duality between Strong Convexity and Lipschitz Continuous Gradientcited by 42
  8. 2020An Online Method for A Class of Distributionally Robust Optimization with Non-Convex Objectivescited by 42
  9. 2018Robust Optimization over Multiple Domainscited by 34
  10. 2019Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradientscited by 32
  11. 2021Asynchronous Stochastic Optimization Robust to Arbitrary Delayscited by 32
  12. 2021Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learningcited by 21
  13. 2015A Practical Guide to Robust Optimizationcited by 16
  14. 2015Asynchronous Distributed ADMM for Large-Scale Optimization- Part I: Algorithm and Convergence Analysiscited by 10
  15. 2022Learning Distributionally Robust Models at Scale via Composite Optimizationcited by 5
  16. 2013A cutting surface algorithm for semi-infinite convex programming with an application to moment robust optimizationcited by 3
  17. 2020Robustness analytics to data heterogeneity in edge computingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 3; 2024: 2; 2025: 3; 2026: 3.

14 papers.

Sort:

  1. 2022Asynchronous Distributed Bilevel Optimizationcited by 13
  2. 2024Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalizationcited by 12
  3. 2023Provably Convergent Federated Trilevel Learningcited by 6
  4. 2023Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challengescited by 5
  5. 2023Federated Distributionally Robust Optimization with Non-Convex Objectives: Algorithm and Analysiscited by 4
  6. 2025Cellular Traffic Prediction via Byzantine-robust Asynchronous Federated Learningcited by 4
  7. 2025Argus: Federated Non-convex Bilevel Learning over 6G Space-Air-Ground Integrated Networkcited by 2
  8. 2022CPMLHO:Hyperparameter Tuning via Cutting Plane and Mixed-Level Optimizationcited by 0
  9. 2022Multi-Level Association Rule Mining for Wireless Network Time Series Datacited by 0
  10. 2024Generalizing Few Data to Unseen Domains Flexibly Based on Label Smoothing Integrated with Distributionally Robust Optimizationcited by 0
  11. 2025Synergistic Localization and Sensing in MIMO-OFDM Systems via Mixed-Integer Bilevel Learningcited by 0
  12. 2026An Adaptive Differentially Private Federated Learning Frameworkcited by 0
2 more
  1. 2026AsynDBT: Asynchronous Distributed Bilevel Tuning for efficient In-Context Learning with Large Language Modelscited by 0
  2. 2026First-order Constrained Trilevel Optimization Over Distributed Networks for Robust Coreset Selectioncited by 0