A Non-Asymptotic Analysis of Mismatched Guesswork
Abstract
The problem of mismatched guesswork considers the additional cost incurred by using a guessing function which is optimal for a distribution when the random variable to be guessed is actually distributed according to a different distribution . This problem has been well-studied from an asymptotic perspective, but there has been little work on quantifying the difference in guesswork between optimal and suboptimal strategies for a finite number of symbols. In this non-asymptotic regime, we consider a definition for mismatched guesswork which we show is equivalent to a variant of the Kendall tau permutation distance applied to optimal guessing functions for the mismatched distributions. We use this formulation to bound the cost of guesswork under mismatch given a bound on the total variation distance between the two distributions.
Keywords
Cite
@article{arxiv.2305.03850,
title = {A Non-Asymptotic Analysis of Mismatched Guesswork},
author = {Alexander Mariona and Homa Esfahanizadeh and Rafael G. L. D'Oliveira and Muriel Médard},
journal= {arXiv preprint arXiv:2305.03850},
year = {2023}
}
Comments
7 pages, 1 figure. Accepted to ISIT 2023