Picture for Nikolas Nüsken

Nikolas Nüsken

Conditioning Diffusions Using Malliavin Calculus

Add code
Apr 04, 2025
Viaarxiv icon

Stein transport for Bayesian inference

Add code
Sep 02, 2024
Viaarxiv icon

From continuous-time formulations to discretization schemes: tensor trains and robust regression for BSDEs and parabolic PDEs

Add code
Jul 28, 2023
Viaarxiv icon

Transport, Variational Inference and Diffusions: with Applications to Annealed Flows and Schrödinger Bridges

Add code
Jul 03, 2023
Figure 1 for Transport, Variational Inference and Diffusions: with Applications to Annealed Flows and Schrödinger Bridges
Figure 2 for Transport, Variational Inference and Diffusions: with Applications to Annealed Flows and Schrödinger Bridges
Figure 3 for Transport, Variational Inference and Diffusions: with Applications to Annealed Flows and Schrödinger Bridges
Figure 4 for Transport, Variational Inference and Diffusions: with Applications to Annealed Flows and Schrödinger Bridges
Viaarxiv icon

Bayesian Learning via Neural Schrödinger-Föllmer Flows

Add code
Dec 07, 2021
Figure 1 for Bayesian Learning via Neural Schrödinger-Föllmer Flows
Figure 2 for Bayesian Learning via Neural Schrödinger-Föllmer Flows
Figure 3 for Bayesian Learning via Neural Schrödinger-Föllmer Flows
Viaarxiv icon

Interpolating between BSDEs and PINNs -- deep learning for elliptic and parabolic boundary value problems

Add code
Dec 07, 2021
Figure 1 for Interpolating between BSDEs and PINNs -- deep learning for elliptic and parabolic boundary value problems
Figure 2 for Interpolating between BSDEs and PINNs -- deep learning for elliptic and parabolic boundary value problems
Figure 3 for Interpolating between BSDEs and PINNs -- deep learning for elliptic and parabolic boundary value problems
Figure 4 for Interpolating between BSDEs and PINNs -- deep learning for elliptic and parabolic boundary value problems
Viaarxiv icon

Stein Variational Gradient Descent: many-particle and long-time asymptotics

Add code
Feb 25, 2021
Figure 1 for Stein Variational Gradient Descent: many-particle and long-time asymptotics
Viaarxiv icon

Solving high-dimensional parabolic PDEs using the tensor train format

Add code
Feb 23, 2021
Figure 1 for Solving high-dimensional parabolic PDEs using the tensor train format
Figure 2 for Solving high-dimensional parabolic PDEs using the tensor train format
Figure 3 for Solving high-dimensional parabolic PDEs using the tensor train format
Figure 4 for Solving high-dimensional parabolic PDEs using the tensor train format
Viaarxiv icon

VarGrad: A Low-Variance Gradient Estimator for Variational Inference

Add code
Oct 29, 2020
Figure 1 for VarGrad: A Low-Variance Gradient Estimator for Variational Inference
Figure 2 for VarGrad: A Low-Variance Gradient Estimator for Variational Inference
Figure 3 for VarGrad: A Low-Variance Gradient Estimator for Variational Inference
Figure 4 for VarGrad: A Low-Variance Gradient Estimator for Variational Inference
Viaarxiv icon

Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space

Add code
May 11, 2020
Figure 1 for Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space
Figure 2 for Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space
Figure 3 for Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space
Figure 4 for Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space
Viaarxiv icon