no code implementations • 23 Mar 2024 • Lorenz Vaitl, Ludwig Winkler, Lorenz Richter, Pan Kessel
Recent work shows that path gradient estimators for normalizing flows have lower variance compared to standard estimators for variational inference, resulting in improved training.
1 code implementation • 28 Jul 2023 • Lorenz Richter, Leon Sallandt, Nikolas Nüsken
The numerical approximation of partial differential equations (PDEs) poses formidable challenges in high dimensions since classical grid-based methods suffer from the so-called curse of dimensionality.
no code implementations • 5 Jul 2023 • Carsten Hartmann, Lorenz Richter
Nevertheless, it is evident that certain specifics of DL that could explain its success in applications demands systematic mathematical approaches.
1 code implementation • 3 Jul 2023 • Lorenz Richter, Julius Berner, Guan-Horng Liu
Recently, a series of papers proposed deep learning-based approaches to sample from unnormalized target densities using controlled diffusion processes.
1 code implementation • 2 Nov 2022 • Julius Berner, Lorenz Richter, Karen Ullrich
In particular, we derive a Hamilton-Jacobi-Bellman equation that governs the evolution of the log-densities of the underlying SDE marginals.
1 code implementation • 21 Jun 2022 • Lorenz Richter, Julius Berner
The combination of Monte Carlo methods and deep learning has recently led to efficient algorithms for solving partial differential equations (PDEs) in high dimensions.
no code implementations • 7 Dec 2021 • Nikolas Nüsken, Lorenz Richter
Solving high-dimensional partial differential equations is a recurrent challenge in economics, science and engineering.
1 code implementation • 23 Feb 2021 • Lorenz Richter, Leon Sallandt, Nikolas Nüsken
High-dimensional partial differential equations (PDEs) are ubiquitous in economics, science and engineering.
1 code implementation • NeurIPS 2020 • Lorenz Richter, Ayman Boustati, Nikolas Nüsken, Francisco J. R. Ruiz, Ömer Deniz Akyildiz
We analyse the properties of an unbiased gradient estimator of the ELBO for variational inference, based on the score function method with leave-one-out control variates.
no code implementations • 11 May 2020 • Nikolas Nüsken, Lorenz Richter
Optimal control of diffusion processes is intimately connected to the problem of solving certain Hamilton-Jacobi-Bellman equations.
1 code implementation • 26 Jan 2019 • Carsten Hartmann, Omar Kebiri, Lara Neureither, Lorenz Richter
We propose an adaptive importance sampling scheme for the simulation of rare events when the underlying dynamics is given by a diffusion.
Probability Optimization and Control 65C05 (primary), 65C30, 92C40 (secondary)