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 the neural networks to construct normalizing flows which are then trained to approximate the desired target distribution. As this distribution is usually defined via a Hamiltonian or action, the standard learning algorithm requires estimation of the action gradient with respect to the fields. In this contribution we present another gradient estimator (and the corresponding [PyTorch implementation) that avoids this calculation, thus potentially speeding up training for models with more complicated actions. We also study the statistical properties of several gradient estimators and show that our formulation leads to better training results.
翻译:最近对蒙特-卡洛模拟的机器学习方法,称为Neural Markov 链链 Monte-Carlo(NMCC)正在获得牵引力,它最流行的形式是利用神经网络来建立正常流动,然后对其进行培训,以接近预期的目标分布。由于这种分布通常通过汉密尔顿语或行动来界定,标准学习算法要求对字段的行动梯度进行估计。在这个贡献中,我们提出了另一个梯度估计器(和相应的[PyTorch 执行器),避免了这一计算,从而有可能加快以更复杂的行动对模型的培训。我们还研究了几个梯度估计器的统计属性,并表明我们的编制方法可以导致更好的培训结果。