arXiv stat.ML
· Papers
Parameter-free Dynamic Regret: Time-varying Movement Costs, Delayed Feedback, and Memory
arXiv:2602.06902v3 Announce Type: replace-cross Abstract: In this paper, we study dynamic regret in unconstrained online convex optimization (OCO) with movement costs. Specifically, we generalize the standard setting by allowing the movement cost coefficients $lambda_t$ to vary arbitrarily over time. Our main contribu