Risk Estimation in a Markov Cost Process: Lower and Upper Bounds
arxiv(2023)
摘要
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].
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要