Preprint
Jul 2026
Parameter-Free Dynamic Regret for Online Convex Optimization under Heavy-Tailed Noise
HT-PAder is proposed, a parameter-free algorithm combining restarted AdaGrad experts over a geometric pool of block lengths with a pathwise meta-algorithm, which requires no moment conditions on meta-losses and provides the first parameter-free minimax universal dynamic regret guarantee.
Vaneet Aggarwal
· 0 citations