A law of large numbers for predicting several steps ahead

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Vovk, Vladimir
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908955969585152
author Vovk, Vladimir
author_facet Vovk, Vladimir
contents This note proves a law of large numbers for predicting several steps ahead, which, in the case of uniformly bounded random variables, generalizes the standard law of large numbers for martingales; the standard law of large numbers corresponds to predicting one step ahead. Its main result shows that the law of large numbers holds for predicting $N$ uniformly bounded random variables $o(N)$ steps ahead, but it is much more precise and in some respects optimal. This law of large numbers is applied to a problem of decision making with a bounded loss function limiting the impact of each decision to $o(N)$ steps.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17507
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A law of large numbers for predicting several steps ahead
Vovk, Vladimir
Probability
60F05, 60G42 (Primary) 60F10, 60G25, 91B06 (Secondary)
This note proves a law of large numbers for predicting several steps ahead, which, in the case of uniformly bounded random variables, generalizes the standard law of large numbers for martingales; the standard law of large numbers corresponds to predicting one step ahead. Its main result shows that the law of large numbers holds for predicting $N$ uniformly bounded random variables $o(N)$ steps ahead, but it is much more precise and in some respects optimal. This law of large numbers is applied to a problem of decision making with a bounded loss function limiting the impact of each decision to $o(N)$ steps.
title A law of large numbers for predicting several steps ahead
topic Probability
60F05, 60G42 (Primary) 60F10, 60G25, 91B06 (Secondary)
url https://arxiv.org/abs/2508.17507