arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.07606cs.LGstat.ML
收藏

尾部风险测度的最优最佳臂辨识方法

Optimal Best-Arm Identification Methods for Tail-Risk Measures

TIFR(塔塔基础研究所);CWI(荷兰国家数学与计算机科学研究所)

Shubhada Agrawal, Wouter M. Koolen, Sandeep Juneja

摘要:

条件风险价值(CVaR)和风险价值(VaR)是金融和保险行业以及高度可靠,安全关键的不确定环境中常用的尾部风险度量,其中潜在的概率分布通常是重尾的。我们使用多臂强盗最佳臂识别框架,并考虑从众多具有最小的CVaR,VaR,或加权总和的CVaR和均值的臂识别的问题。后者抓住了金融中常见的风险回报权衡。我们的主要贡献是一个最佳的$δ$正确的算法,作用于一般武器,包括重尾分布,并匹配所需的样本的预期数量的下限,渐近(作为$δ$方法$0$)。该算法需要解决概率测度空间中的非凸优化问题,这需要精细的分析。途中,我们开发了新的非渐近的经验似然为基础的浓度不等式的尾部风险的措施,这是严格的比流行的截断为基础的经验估计。

英文摘要:

Conditional value-at-risk (CVaR) and value-at-risk (VaR) are popular tail-risk measures in finance and insurance industries as well as in highly reliable, safety-critical uncertain environments where often the underlying probability distributions are heavy-tailed. We use the multi-armed bandit best-arm identification framework and consider the problem of identifying the arm from amongst finitely many that has the smallest CVaR, VaR, or weighted sum of CVaR and mean. The latter captures the risk-return trade-off common in finance. Our main contribution is an optimal $δ$-correct algorithm that acts on general arms, including heavy-tailed distributions, and matches the lower bound on the expected number of samples needed, asymptotically (as $δ$ approaches $0$). The algorithm requires solving a non-convex optimization problem in the space of probability measures, that requires delicate analysis. En-route, we develop new non-asymptotic empirical likelihood-based concentration inequalities for tail-risk measures which are tighter than those for popular truncation-based empirical estimators.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑