arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.15460physics.comp-ph
收藏

基于人工神经网络的变分蒙特卡洛方法简介

Introduction to the artificial neural network-based variational Monte Carlo method

Max Planck Institute for the Physics of Complex Systems(马克斯·普朗克复杂系统物理研究所)

William Freitas

AI总结:

本文介绍了基于神经网络的变分蒙特卡洛方法,探讨了如何利用神经网络构建试波函数,分析了此类试波函数的优势以及机器学习在其中的作用,指出变分法是一种无监督学习算法,并通过尤拉-韦尔模型和氢分子示例展示了算法的应用。

摘要:

讨论了基于神经网络构建试波函数与变分蒙特卡洛方法结合的构造。介绍了将量子态表示为人工神经网络的数学公式。讨论了使用此类试波函数的优势以及机器学习如何发挥作用。证明了变分法是一种无监督学习算法,其中多重极小景观被用作资产,从而导致稳定的优化过程。特征表示在可解释性和从非平凡试波函数中提取物理见解方面起着重要作用。该算法通过尤拉-韦尔势和氢分子进行了说明。

英文摘要:

The construction of trial wave functions based on neural networks combined with the variational Monte Carlo method is discussed. The mathematical formulation for representing quantum states as artificial neural networks is introduced. The advantages of employing such trial states and how machine learning works are discussed. It is shown that the variational method is a kind of unsupervised learning algorithm, where the multiple minima landscape is used as an asset that leads to a stable optimization procedure. The feature representation plays an important role on interpretability and on extracting physical insights from nontrivial trial wave functions. The algorithm is illustrated for the Yukawa potential and the hydrogen molecule.

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。

↑