collaborators
Showing stat.MLShow all

5 papers · 1 filter

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 proc…

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…

stat.ML2024

Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs

Florian Krach, Marc Nübel, Marc Nübel +1

This paper studies the problem of forecasting general stochastic processes using a path-dependent extension of the Neural Jump ODE (NJ-ODE) framework \citep{herrera2021neural}. Whi…

stat.ML2024

Extending Path-Dependent NJ-ODEs to Noisy Observations and a Dependent Observation Framework

William Andersson, Jakob Heiss, Florian Krach +1

The Path-Dependent Neural Jump Ordinary Differential Equation (PD-NJ-ODE) is a model for predicting continuous-time stochastic processes with irregular and incomplete observations.…