OpenAlex ·
Projection-Free Bandit Online Optimization for Multi-Agent Systems with Dynamic Regret
- Published
- Source
- OpenAlex
- Published in
- arXiv (Cornell University)
- DOI
- 10.48550/arxiv.2608.30159
- Original
- Read it at the publisher
- Topics
Abstract
This paper investigates distributed online optimization for multi-agent dynamical systems with constrained inputs and time-varying cost functions. While online convex optimization offers a principal framework for sequential decision-making, existing online learning and optimization algorithms typically require accurate system models, limiting their applicability in practical settings. To overcome this challenge, we propose a distributed bandit online feedback optimization algorithm that relies solely on real-time input-output data. The algorithm employs a smoothing zeroth-order one-point estimator to construct local gradient approximations directly from cost evaluations. Additionally, to enforce input constraints effectively, we integrate a projection-free conditional gradient update, making the algorithm well-suited for online and large-scale settings. Furthermore, we establish a sublinear dynamic regret bound that depends on a temporal variation measure of system non-stationarity. Finally, numerical simulations demonstrate the effectiveness of the proposed algorithm.
The authors’ abstract, as arXiv lists it. arXiv’s listings, abstracts included, are free for anyone to reuse.
Read it on ReadSearch
Each opens after you create an account, and brings you back to this paper.
More in Networking & Internet
Provably Safe Decentralized Contingency MPC under State-Only Information and Limited Sensing for Nonlinear Multi-agent Systems
Prediction-Assisted Pricing and Admission for LLM APIs with Stochastic Token Consumption
Ray Tracing-Based LoRaWAN Gateway Placement for Reliable Connectivity in Amazonian Regions
Weighted Fair Division of Indivisible Mixed Manna
Tight Maximin Share Guarantees of EFX and PMMS
Get the few papers worth your time in Networking & Internet every morning.
ReadSearch reads the new papers in your field each day and brings you the few worth reading, each with its key finding in a sentence.