Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

EV-GAN: Simulation of extreme events with ReLU neural networks

Abstract : Feedforward neural networks based on Rectified linear units (ReLU) cannot efficiently approximate quantile functions which are not bounded, especially in the case of heavy-tailed distributions. We thus propose a new parametrization for the generator of a Generative adversarial network (GAN) adapted to this framework, basing on extreme-value theory. We provide an analysis of the uniform error between the extreme quantile and its GAN approximation. It appears that the rate of convergence of the error is mainly driven by the second-order parameter of the data distribution. The above results are illustrated on simulated data and real financial data.
Document type :
Preprints, Working Papers, ...
Complete list of metadata
Contributor : Stephane Girard <>
Submitted on : Wednesday, June 16, 2021 - 9:41:13 AM
Last modification on : Wednesday, June 23, 2021 - 12:36:03 PM


Files produced by the author(s)


  • HAL Id : hal-03250663, version 2



Michaël Allouche, Stéphane Girard, Emmanuel Gobet. EV-GAN: Simulation of extreme events with ReLU neural networks. 2021. ⟨hal-03250663v2⟩



Record views


Files downloads