English

PAC-Bayes Iterated Logarithm Bounds for Martingale Mixtures

Machine Learning 2015-06-23 v1 Probability Machine Learning

Abstract

We give tight concentration bounds for mixtures of martingales that are simultaneously uniform over (a) mixture distributions, in a PAC-Bayes sense; and (b) all finite times. These bounds are proved in terms of the martingale variance, extending classical Bernstein inequalities, and sharpening and simplifying prior work.

Keywords

Cite

@article{arxiv.1506.06573,
  title  = {PAC-Bayes Iterated Logarithm Bounds for Martingale Mixtures},
  author = {Akshay Balsubramani},
  journal= {arXiv preprint arXiv:1506.06573},
  year   = {2015}
}
R2 v1 2026-06-22T09:57:50.371Z