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

1 citations · 1 across the 1 of their papers we have counts for

collaborators

1 paper

cs.LG2022★ 1 cited

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…