L
Lorenz Richter
Researcher at Free University of Berlin
Publications - 18
Citations - 185
Lorenz Richter is an academic researcher from Free University of Berlin. The author has contributed to research in topics: Computer science & Importance sampling. The author has an hindex of 5, co-authored 11 publications receiving 100 citations. Previous affiliations of Lorenz Richter include Brandenburg University of Technology.
Papers
More filters
Solving high-dimensional Hamilton–Jacobi–Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space
TL;DR: The potential of iterative diffusion optimisation techniques is investigated, in particular considering applications in importance sampling and rare event simulation, and focusing on problems without diffusion control, with linearly controlled drift and running costs that depend quadratically on the control.
Journal ArticleDOI
Variational Characterization of Free Energy: Theory and Algorithms
TL;DR: The article revisits the well-known Jarzynski equality for nonequilibrium free energy sampling within the framework of importance sampling and Girsanov change-of-measure transformations and discusses their information-theoretic content from the perspective of mathematical statistics.
Posted Content
Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space
Nikolas Nüsken,Lorenz Richter +1 more
TL;DR: In this paper, the authors investigated the potential of iterative diffusion optimisation techniques, in particular considering applications in importance sampling and rare event simulation, and developed a principled framework based on divergences between path measures.
Journal ArticleDOI
Variational approach to rare event simulation using least-squares regression
TL;DR: An adaptive importance sampling scheme for the simulation of rare events when the underlying dynamics is given by diffusion is proposed, based on a Gibbs variational principle that is used to determine the optimal change of measure.
Proceedings Article
VarGrad: A Low-Variance Gradient Estimator for Variational Inference
TL;DR: It is empirically demonstrated that VarGrad offers a favourable variance versus computation trade-off compared to other state-of-the-art estimators on a discrete VAE.