Gradient estimators for normalising flows
This work addresses efficiency in Monte-Carlo simulations for physics models, though it appears incremental as it improves an existing method.
The authors tackled the problem of training normalizing flows for Neural Markov Chain Monte-Carlo by introducing a new gradient estimator for Stochastic Gradient Descent, which achieved the same precision in approximately half the time and better free energy estimates for the φ⁴ model.
Recently a machine learning approach to Monte-Carlo simulations called Neural Markov Chain Monte-Carlo (NMCMC) is gaining traction. In its most popular form it uses neural networks to construct normalizing flows which are then trained to approximate the desired target distribution. In this contribution we present new gradient estimator for Stochastic Gradient Descent algorithm (and the corresponding \texttt{PyTorch} implementation) and show that it leads to better training results for $φ^4$ model. For this model our estimator achieves the same precision in approximately half of the time needed in standard approach and ultimately provides better estimates of the free energy. We attribute this effect to the lower variance of the new estimator. In contrary to the standard learning algorithm our approach does not require estimation of the action gradient with respect to the fields, thus has potential of further speeding up the training for models with more complicated actions.