33 citations · 42 across the 4 of their papers we have counts for
5 papers
Path Gradients after Flow Matching
Lorenz Vaitl, Leon Klein
Boltzmann Generators have emerged as a promising machine learning tool for generating samples from equilibrium distributions of molecular systems using Normalizing Flows and import…
Fast and Unified Path Gradient Estimators for Normalizing Flows
Lorenz Vaitl, Ludwig Winkler, Lorenz Richter +1
Recent work shows that path gradient estimators for normalizing flows have lower variance compared to standard estimators for variational inference, resulting in improved training.…
Learning Trivializing Gradient Flows for Lattice Gauge Theories
Simone Bacchio, Pan Kessel, Stefan Schaefer +1
We propose a unifying approach that starts from the perturbative construction of trivializing maps by Lüscher and then improves on it by learning. The resulting continuous normaliz…
Gradients should stay on Path: Better Estimators of the Reverse- and Forward KL Divergence for Normalizing Flows
Lorenz Vaitl, Kim A. Nicoli, Shinichi Nakajima +1
We propose an algorithm to estimate the path-gradient of both the reverse and forward Kullback-Leibler divergence for an arbitrary manifestly invertible normalizing flow. The resul…
Path-Gradient Estimators for Continuous Normalizing Flows
Lorenz Vaitl, Kim A. Nicoli, Shinichi Nakajima +1
Recent work has established a path-gradient estimator for simple variational Gaussian distributions and has argued that the path-gradient is particularly beneficial in the regime i…