ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2104.11824
37
43

Optimal Dynamic Regret in Exp-Concave Online Learning

23 April 2021
Dheeraj Baby
Yu-Xiang Wang
ArXivPDFHTML
Abstract

We consider the problem of the Zinkevich (2003)-style dynamic regret minimization in online learning with exp-concave losses. We show that whenever improper learning is allowed, a Strongly Adaptive online learner achieves the dynamic regret of O~∗(n1/3Cn2/3∨1)\tilde O^*(n^{1/3}C_n^{2/3} \vee 1)O~∗(n1/3Cn2/3​∨1) where CnC_nCn​ is the total variation (a.k.a. path length) of the an arbitrary sequence of comparators that may not be known to the learner ahead of time. Achieving this rate was highly nontrivial even for squared losses in 1D where the best known upper bound was O(nCn∨log⁡n)O(\sqrt{nC_n} \vee \log n)O(nCn​​∨logn) (Yuan and Lamperski, 2019). Our new proof techniques make elegant use of the intricate structures of the primal and dual variables imposed by the KKT conditions and could be of independent interest. Finally, we apply our results to the classical statistical problem of locally adaptive non-parametric regression (Mammen, 1991; Donoho and Johnstone, 1998) and obtain a stronger and more flexible algorithm that do not require any statistical assumptions or any hyperparameter tuning.

View on arXiv
Comments on this paper