3 papers
stat.ML2026
Operator Neural Jump ODEs: -optimal prediction in function spaces
Florian Krach, Oliver Löthgren, Josef Teichmann
In this paper, we study the extension of Neural Jump ODEs to infinite-dimensional function spaces. In particular, the underlying process now takes values in $L^2(Ξ, \mathbb{R}^…
stat.ML2025
Neural Jump ODEs as Generative Models
Robert A. Crowell, Florian Krach, Josef Teichmann
In this work, we explore how Neural Jump ODEs (NJODEs) can be used as generative models for Itô processes. Given (discrete observations of) samples of a fixed underlying Itô proces…
stat.ML2024
Learning Chaotic Systems and Long-Term Predictions with Neural Jump ODEs
Florian Krach, Josef Teichmann
The Path-dependent Neural Jump ODE (PD-NJ-ODE) is a model for online prediction of generic (possibly non-Markovian) stochastic processes with irregular (in time) and potentially in…