Gradients should stay on Path: Better Estimators of the Reverse- and Forward KL Divergence for Normalizing Flows

17 July 2022

Papers citing "Gradients should stay on Path: Better Estimators of the Reverse- and Forward KL Divergence for Normalizing Flows"

4 / 4 papers shown

Title
Stable Training of Normalizing Flows for High-dimensional Variational Inference Daniel Andrade BDL TPM 43 1 0 26 Feb 2024
Detecting and Mitigating Mode-Collapse for Flow-based Sampling of Lattice Field Theories K. Nicoli Christopher J. Anders T. Hartung K. Jansen Pan Kessel Shinichi Nakajima 24 22 0 27 Feb 2023
VarGrad: A Low-Variance Gradient Estimator for Variational Inference Lorenz Richter Ayman Boustati Nikolas Nusken Francisco J. R. Ruiz Ömer Deniz Akyildiz DRL 127 48 0 20 Oct 2020
On the Difficulty of Unbiased Alpha Divergence Minimization Tomas Geffner Justin Domke 46 18 0 19 Oct 2020