AI RESEARCH
Structure-Dependent Regret and Constraint Violation Bounds for Online Convex Optimization with Time-Varying Constraints
arXiv CS.LG
•
ArXi:2603.14319v1 Announce Type: new Online convex optimization (OCO) with time-varying constraints is a critical framework for sequential decision-making in dynamic networked systems, where learners must minimize cumulative loss while satisfying regions of feasibility that shift across rounds. Existing theoretical analyses typically treat constraint variation as a monolithic adversarial process, resulting in joint regret and violation bounds that are overly conservative for real-world network dynamics. In this paper, we.