On Confidence Sequences for Bounded Random Processes via Universal Gambling Strategies

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ryu, J. Jon, Bhatt, Alankrita
Natura: Preprint
Pubblicazione: 2022
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914921629876224
author Ryu, J. Jon
Bhatt, Alankrita
author_facet Ryu, J. Jon
Bhatt, Alankrita
contents This paper considers the problem of constructing a confidence sequence, which is a sequence of confidence intervals that hold uniformly over time, for estimating the mean of bounded real-valued random processes. This paper revisits the gambling-based approach established in the recent literature from a natural \emph{two-horse race} perspective, and demonstrates new properties of the resulting algorithm induced by Cover (1991)'s universal portfolio. The main result of this paper is a new algorithm based on a mixture of lower bounds, which closely approximates the performance of Cover's universal portfolio with constant per-round time complexity. A higher-order generalization of a lower bound on a logarithmic function in (Fan et al., 2015), which is developed as a key technique for the proposed algorithm, may be of independent interest.
format Preprint
id arxiv_https___arxiv_org_abs_2207_12382
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle On Confidence Sequences for Bounded Random Processes via Universal Gambling Strategies
Ryu, J. Jon
Bhatt, Alankrita
Probability
Information Theory
Methodology
This paper considers the problem of constructing a confidence sequence, which is a sequence of confidence intervals that hold uniformly over time, for estimating the mean of bounded real-valued random processes. This paper revisits the gambling-based approach established in the recent literature from a natural \emph{two-horse race} perspective, and demonstrates new properties of the resulting algorithm induced by Cover (1991)'s universal portfolio. The main result of this paper is a new algorithm based on a mixture of lower bounds, which closely approximates the performance of Cover's universal portfolio with constant per-round time complexity. A higher-order generalization of a lower bound on a logarithmic function in (Fan et al., 2015), which is developed as a key technique for the proposed algorithm, may be of independent interest.
title On Confidence Sequences for Bounded Random Processes via Universal Gambling Strategies
topic Probability
Information Theory
Methodology
url https://arxiv.org/abs/2207.12382