![[2602.10452] Distributed Online Convex Optimization with Nonseparable Costs and Constraints](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.10452] Distributed Online Convex Optimization with Nonseparable Costs and Constraints
Summary
This paper explores distributed online convex optimization with nonseparable costs and constraints, presenting a novel algorithm that improves efficiency in networked systems.
Why It Matters
Understanding distributed online convex optimization is crucial for advancements in networked control systems. This research addresses limitations in existing methods by proposing a new algorithm that enhances performance while managing communication overhead, thereby contributing to more efficient online learning frameworks.
Key Takeaways
- Introduces a distributed online primal-dual belief consensus algorithm.
- Breaks the O(T^{3/4}) barrier for cumulative constraint violation.
- Demonstrates sublinear regret and cumulative constraint violation bounds.
- Focuses on nonseparable global cost functions in networked systems.
- Highlights the trade-off between learning efficiency and communication overhead.
Mathematics > Optimization and Control arXiv:2602.10452 (math) [Submitted on 11 Feb 2026 (v1), last revised 17 Feb 2026 (this version, v2)] Title:Distributed Online Convex Optimization with Nonseparable Costs and Constraints Authors:Zhaoye Pan, Haozhe Lei, Fan Zuo, Zilin Bian, Tao Li View a PDF of the paper titled Distributed Online Convex Optimization with Nonseparable Costs and Constraints, by Zhaoye Pan and 4 other authors View PDF HTML (experimental) Abstract:This paper studies distributed online convex optimization with time-varying coupled constraints, motivated by distributed online control in network systems. Most prior work assumes a separability condition: the global objective and coupled constraint functions are sums of local costs and individual constraints. In contrast, we study a group of agents, networked via a communication graph, that collectively select actions to minimize a sequence of nonseparable global cost functions and to satisfy nonseparable long-term constraints based on full-information feedback and intra-agent communication. We propose a distributed online primal-dual belief consensus algorithm, where each agent maintains and updates a local belief of the global collective decisions, which are repeatedly exchanged with neighboring agents. Unlike the previous consensus primal-dual algorithms under separability that ask agents to only communicate their local decisions, our belief-sharing protocol eliminates coupling between the primal consensus di...
