arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2202.01314stat.MLcond-mat.stat-mechcs.LGhep-lat
收藏

归一化流的梯度估计

Gradient estimators for normalising flows

Jagiellonian University(雅盖隆大学)

Piotr Bialas, Piotr Korcyl, Tomasz Stebel

摘要:

最近,一种称为神经马尔可夫链蒙特卡罗(NMCMC)的蒙特卡罗模拟机器学习方法正在获得关注。在其最流行的形式中,它使用神经网络来构建规范化流,然后对规范化流进行训练以近似期望的目标分布。在这篇文章中,我们提出了新的梯度估计随机梯度下降算法(和相应的\texttt{PyTorch}实现),并表明它导致更好的训练结果$ϕ^4$模型。对于这个模型,我们的估计器在标准方法所需时间的大约一半内实现了相同的精度,并最终提供了更好的自由能估计。我们将这种效应归因于新估计量的较低方差。与标准学习算法相反,我们的方法不需要估计相对于场的动作梯度,因此具有进一步加快具有更复杂动作的模型的训练的潜力。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑