Training normalizing flows with computationally intensive target probability distributions

arXiv:2308.13294v2 Announce Type: replace
Abstract: Machine learning techniques, in particular the so-called normalizing flows, are becoming increasingly popular in the context of Monte Carlo simulations as they can effectively approximate target probability distributions. In the case of lattice field theories (LFT) the target distribution is given by the exponential of the action. The common loss function's gradient estimator based on the "reparametrization trick" requires the calculation of the derivative of the action with respect to the fields. This can present …

abstract arxiv case cond-mat.stat-mech context cs.lg distribution lattice machine machine learning machine learning techniques popular probability simulations training type