Risk Estimation in a Markov Cost Process: Lower and Upper Bounds

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Thoppe, Gugan, Prashanth, L. A., Bhat, Sanjay
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910405699305472
author Thoppe, Gugan
Prashanth, L. A.
Bhat, Sanjay
author_facet Thoppe, Gugan
Prashanth, L. A.
Bhat, Sanjay
contents We tackle the problem of estimating risk measures of the infinite-horizon discounted cost within a Markov cost process. The risk measures we study include variance, Value-at-Risk (VaR), and Conditional Value-at-Risk (CVaR). First, we show that estimating any of these risk measures with $ε$-accuracy, either in expected or high-probability sense, requires at least $Ω(1/ε^2)$ samples. Then, using a truncation scheme, we derive an upper bound for the CVaR and variance estimation. This bound matches our lower bound up to logarithmic factors. Finally, we discuss an extension of our estimation scheme that covers more general risk measures satisfying a certain continuity criterion, e.g., spectral risk measures, utility-based shortfall risk. To the best of our knowledge, our work is the first to provide lower and upper bounds for estimating any risk measure beyond the mean within a Markovian setting. Our lower bounds also extend to the infinite-horizon discounted costs' mean. Even in that case, our lower bound of $Ω(1/ε^2) $ improves upon the existing $Ω(1/ε)$ bound [13].
format Preprint
id arxiv_https___arxiv_org_abs_2310_11389
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Risk Estimation in a Markov Cost Process: Lower and Upper Bounds
Thoppe, Gugan
Prashanth, L. A.
Bhat, Sanjay
Machine Learning
We tackle the problem of estimating risk measures of the infinite-horizon discounted cost within a Markov cost process. The risk measures we study include variance, Value-at-Risk (VaR), and Conditional Value-at-Risk (CVaR). First, we show that estimating any of these risk measures with $ε$-accuracy, either in expected or high-probability sense, requires at least $Ω(1/ε^2)$ samples. Then, using a truncation scheme, we derive an upper bound for the CVaR and variance estimation. This bound matches our lower bound up to logarithmic factors. Finally, we discuss an extension of our estimation scheme that covers more general risk measures satisfying a certain continuity criterion, e.g., spectral risk measures, utility-based shortfall risk. To the best of our knowledge, our work is the first to provide lower and upper bounds for estimating any risk measure beyond the mean within a Markovian setting. Our lower bounds also extend to the infinite-horizon discounted costs' mean. Even in that case, our lower bound of $Ω(1/ε^2) $ improves upon the existing $Ω(1/ε)$ bound [13].
title Risk Estimation in a Markov Cost Process: Lower and Upper Bounds
topic Machine Learning
url https://arxiv.org/abs/2310.11389