4 papers
On adversarial robustness and the use of Wasserstein ascent-descent dynamics to enforce it
Camilo Garcia Trillos, Nicolas Garcia Trillos
We propose iterative algorithms to solve adversarial problems in a variety of supervised learning settings of interest. Our algorithms, which can be interpreted as suitable ascent-…
On the regularized risk of distributionally robust learning over deep neural networks
Camilo Garcia Trillos, Nicolas Garcia Trillos
In this paper we explore the relation between distributionally robust learning and different forms of regularization to enforce robustness of deep neural networks. In particular, s…
A sparse grid approach to balance sheet risk measurement
Cyril Bénézet, Jérémie Bonnefoy, Jean-François Chassagneux +3
In this work, we present a numerical method based on a sparse grid approximation to compute the loss distribution of the balance sheet of a financial or an insurance company. We fi…
Cubature methods to solve BSDEs: Error expansion and complexity control
Jean-François Chassagneux, Camilo A. Garcia Trillos
We obtain an explicit error expansion for the solution of Backward Stochastic Differential Equations (BSDEs) using the cubature on Wiener spaces method. The result is proved under…