Asymptotic Error Analysis of Multilevel Stochastic Approximations for the Value-at-Risk and Expected Shortfall

1 code implementation • 26 Nov 2023 • Stéphane Crépey, Noufel Frikha, Azar Louzi, Gilles Pagès

This article is a follow up to Cr\'epey, Frikha, and Louzi (2023), where we introduced a nested stochastic approximation algorithm and its multilevel acceleration for computing the value-at-risk and expected shortfall of a random financial loss.

A Multilevel Stochastic Approximation Algorithm for Value-at-Risk and Expected Shortfall Estimation

1 code implementation • 24 Mar 2023 • Stéphane Crépey, Noufel Frikha, Azar Louzi

We propose a multilevel stochastic approximation (MLSA) scheme for the computation of the Value-at-Risk (VaR) and the Expected Shortfall (ES) of a financial loss, which can only be computed via simulations conditional on the realization of future risk factors.

Actor-Critic learning for mean-field control in continuous time

no code implementations • 13 Mar 2023 • Noufel Frikha, Maximilien Germain, Mathieu Laurière, Huyên Pham, Xuanye Song

We study policy gradient for mean-field control in continuous time in a reinforcement learning setting.

reinforcement-learning Reinforcement Learning (RL)