We propose a non-asymptotic convergence analysis of a two-step approach to learn a conditional value-at-risk (VaR) and expected shortfall (ES) in a nonparametric setting using Rademacher and Vapnik-Chervonenkis bounds. Our approach for the VaR is extended to the problem of learning at once multiple VaRs corresponding to different quantile levels. This results in efficient learning schemes based on neural network quantile and least-squares regressions. An a posteriori Monte Carlo (non-nested) procedure is introduced to estimate distances to the ground-truth VaR and ES without access to the latter. This is illustrated using numerical experiments in a Gaussian toy-model and a financial case-study where the objective is to learn a dynamic initial margin.
翻译:我们建议对两步方法进行非抽吸趋同分析,以便利用Rademacher和Vapnik-Chervonenkis界限,在非参数环境中学习有条件的风险值和预期的短缺值。我们对于VaR的方法将扩展至与不同四分位水平相对应的多次空位的学习问题。这导致以神经网络孔径和最小方位回归为基础的高效学习计划。引入了一个后传蒙特卡洛(不遗漏)程序,以估计与地面轨迹VaR和ES的距离,而不能与后者接触。在高山玩具模型中进行数字实验,并进行财务案例研究,目的是学习动态的初步差数。