mlsanityData to 14 Oct 2026

Learning-Augmented Decentralized Online Convex Optimization in Networks

arXiv 2306.10158 ↗First posted 16 Jun 2023cs.LG math.OCcited by 1

Not on the map. Why?

Abstract (arXiv)

This paper studies decentralized online convex optimization in a networked multi-agent system and proposes a novel algorithm, Learning-Augmented Decentralized Online optimization (LADO), for individual agents to select actions only based on local online information. LADO leverages a baseline policy to safeguard online actions for worst-case robustness guarantees, while staying close to the machine learning (ML) policy for average performance improvement. In stark contrast with the existing learning-augmented online algorithms that focus on centralized settings, LADO achieves strong robustness guarantees in a decentralized setting. We also prove the average cost bound for LADO, revealing the tradeoff between average performance and worst-case robustness and demonstrating the advantage of training the ML policy by explicitly considering the robustness requirement.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 38 of its 76 references that are in the map. First posted on arXiv 16 Jun 2023.

Builds on

38 of 76 references.

References · 38

  1. 2019Introduction to Online Convex Optimizationcited by 803
  2. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 567
  3. 2019Differentiable Convex Optimization Layerscited by 465
  4. 2018Competitive caching with machine learned advicecited by 195
  5. 2018Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agentscited by 194
  6. 2019A Review of Cooperative Multi-Agent Deep Reinforcement Learningcited by 147
  7. 2019Exploratory Combinatorial Optimization with Reinforcement Learningcited by 82
  8. 2020The Primal-Dual method for Learning Augmented Algorithmscited by 80
  9. 2020Online metric algorithms with untrusted predictionscited by 75
  10. 2018Multi-Agent Deep Reinforcement Learning for Dynamic Power Allocation in Wireless Networkscited by 70
  11. 2020Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithmscited by 64
  12. 2020Single and Multi-Agent Deep Reinforcement Learning for AI-Enabled Wireless Networks: A Tutorialcited by 60
26 more
  1. 2016Conservative Banditscited by 59
  2. 2021Carbon-Aware Computing for Datacenterscited by 41
  3. 2019Control Regularization for Reduced Variance Reinforcement Learningcited by 37
  4. 2018Smoothed Online Convex Optimization in High Dimensions via Online Balanced Descentcited by 33
  5. 2019Beyond Online Balanced Descent: An Optimal Algorithm for Smoothed Online Optimizationcited by 31
  6. 2021Revisiting Smoothed Online Learningcited by 29
  7. 2020Conservative Exploration in Reinforcement Learningcited by 20
  8. 2022Chasing Convex Bodies and Functions with Black-Box Advicecited by 19
  9. 2022Bounded-Regret MPC via Perturbation Analysis: Prediction Error, Constraints, and Nonlinearitycited by 16
  10. 2014Online Distributed Optimization on Dynamic Networkscited by 15
  11. 2021Stability Constrained Reinforcement Learning for Real-Time Voltage Controlcited by 15
  12. 2021Robust Learning-Augmented Caching: An Experimental Studycited by 12
  13. 2022A Regression Approach to Learning-Augmented Online Algorithmscited by 12
  14. 2018A Collaborative Multi-agent Reinforcement Learning Anti-jamming Algorithm in Wireless Networkscited by 10
  15. 2022Smoothed Online Optimization with Unreliable Predictionscited by 10
  16. 2016Smooth Imitation Learning for Online Sequence Predictioncited by 9
  17. 2021A Reduction-Based Framework for Conservative Bandits and Reinforcement Learningcited by 9
  18. 2020Distributed Online Convex Optimization with an Aggregative Variablecited by 7
  19. 2020Learning Robust Algorithms for Online Allocation Problems Using Adversarial Trainingcited by 6
  20. 2022Expert-Calibrated Learning for Online Optimization with Switching Costscited by 6
  21. 2017Collaborative Deep Reinforcement Learningcited by 5
  22. 2021Online Optimization with Feedback Delay and Nonlinear Switching Costcited by 5
  23. 2023Learning for Edge-Weighted Online Bipartite Matching with Robustness Guaranteescited by 5
  24. 2021Learning for Robust Combinatorial Optimization: Algorithm and Applicationcited by 4
  25. 2022Decentralized Online Convex Optimization in Networked Systemscited by 4
  26. 2023Robustified Learning for Online Optimization with Memory Costscited by 4

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Signal-Aware Workload Shifting Algorithms with Uncertainty-Quantified Predictorscited by 0