Optimal Stopping via Randomized Neural Networks

2 code implementations • 28 Apr 2021 • Calypso Herrera, Florian Krach, Pierre Ruyssen, Josef Teichmann

This paper presents the benefits of using randomized neural networks instead of standard basis functions or deep neural networks to approximate the solutions of optimal stopping problems.

BIG-bench Machine Learning

Neural Jump Ordinary Differential Equations: Consistent Continuous-Time Prediction and Filtering

2 code implementations • ICLR 2021 • Calypso Herrera, Florian Krach, Josef Teichmann

We introduce the Neural Jump ODE (NJ-ODE) that provides a data-driven approach to learn, continuously in time, the conditional expectation of a stochastic process.

Time Series Time Series Analysis

Denise: Deep Robust Principal Component Analysis for Positive Semidefinite Matrices

1 code implementation • 28 Apr 2020 • Calypso Herrera, Florian Krach, Anastasis Kratsios, Pierre Ruyssen, Josef Teichmann

The robust PCA of covariance matrices plays an essential role when isolating key explanatory features.

Local Lipschitz Bounds of Deep Neural Networks

no code implementations • 27 Apr 2020 • Calypso Herrera, Florian Krach, Josef Teichmann

The Lipschitz constant is an important quantity that arises in analysing the convergence of gradient-based optimization methods.