Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability

Non-stationary online learning has drawn much attention in recent years. Despite considerable progress, dynamic regret minimization has primarily focused on convex functions, leaving the functions with stronger curvature (e.g., squared or logistic loss) underexplored. In this work, we address this gap by showing that the regret can be substantially improved by leveraging the concept of mixability, a property that generalizes expconcavity to effectively capture loss curvature. Let d denote the dimensionality and P T the path length of comparators that reflects the environmental non-stationarity. We demonstrate that an exponential-weight method with fixed-share updates achieves an O(dT 1/3 P 2/3 T log T ) dynamic regret for mixable losses, improving upon the bestknown O(d 10/3 T 1/3 P 2/3 T log T ) result (Baby & Wang, 2021) in d. More importantly, this improvement arises from a simple yet powerful analytical framework that exploits the mixability, which avoids the Karush-Kuhn-Tucker-based analysis required by existing work.