Generic Bounds on the Maximum Deviations in Sequential Prediction: An Information-Theoretic Analysis
Machine Learning
2021-05-12 v3 Information Theory
Signal Processing
math.IT
Statistics Theory
Machine Learning
Statistics Theory
Abstract
In this paper, we derive generic bounds on the maximum deviations in prediction errors for sequential prediction via an information-theoretic approach. The fundamental bounds are shown to depend only on the conditional entropy of the data point to be predicted given the previous data points. In the asymptotic case, the bounds are achieved if and only if the prediction error is white and uniformly distributed.
Cite
@article{arxiv.1910.06742,
title = {Generic Bounds on the Maximum Deviations in Sequential Prediction: An Information-Theoretic Analysis},
author = {Song Fang and Quanyan Zhu},
journal= {arXiv preprint arXiv:1910.06742},
year = {2021}
}
Comments
arXiv admin note: text overlap with arXiv:1904.04765. text overlap with arXiv:2001.03813