English

Online Prediction in Sub-linear Space

Data Structures and Algorithms 2022-11-09 v2 Machine Learning

Abstract

We provide the first sub-linear space and sub-linear regret algorithm for online learning with expert advice (against an oblivious adversary), addressing an open question raised recently by Srinivas, Woodruff, Xu and Zhou (STOC 2022). We also demonstrate a separation between oblivious and (strong) adaptive adversaries by proving a linear memory lower bound of any sub-linear regret algorithm against an adaptive adversary. Our algorithm is based on a novel pool selection procedure that bypasses the traditional wisdom of leader selection for online learning, and a generic reduction that transforms any weakly sub-linear regret o(T)o(T) algorithm to T1αT^{1-\alpha} regret algorithm, which may be of independent interest. Our lower bound utilizes the connection of no-regret learning and equilibrium computation in zero-sum games, leading to a proof of a strong lower bound against an adaptive adversary.

Keywords

Cite

@article{arxiv.2207.07974,
  title  = {Online Prediction in Sub-linear Space},
  author = {Binghui Peng and Fred Zhang},
  journal= {arXiv preprint arXiv:2207.07974},
  year   = {2022}
}
R2 v1 2026-06-25T00:58:27.911Z