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 2106.10558stat.MLcs.LGcs.NAmath.NAphysics.chem-ph
收藏

用于变分蒙特卡洛的增强采样 Rayleigh-Gauss-Newton 优化

Rayleigh-Gauss-Newton optimization with enhanced sampling for variational Monte Carlo

Courant Institute of Mathematical Sciences, New York University(纽约大学库朗数学科学研究所)

Robert J. Webber, Michael Lindsey

AI总结:

针对变分蒙特卡洛中神经波函数优化难、采样噪声大的问题,提出 Rayleigh-Gauss-Newton 优化器并结合 parallel tempering 增强采样,在大晶格 Ising 与 XXZ 模型上实现快速高精度基态能量估计。

摘要:

变分蒙特卡洛(VMC)是一种计算基态波函数的方法,随着基于神经网络的波函数参数化的引入,其近来变得更加强大。然而,高效训练神经波函数以收敛到能量极小值仍然是一个难题。在本工作中,我们分析了 VMC 中使用的优化和采样方法,并引入改进以提升其性能。首先,基于无噪声情形下的理论收敛分析,我们提出了一种新的优化器,称为 Rayleigh-Gauss-Newton 方法;它能够改进梯度下降和自然梯度下降,以不超过两倍的计算成本实现超线性收敛。其次,为了在存在随机噪声时实现这一有利比较,我们分析了采样误差对 VMC 参数更新的影响,并通过实验证明 parallel tempering 方法可以降低该误差。特别地,我们证明 RGN 能够对采样器在构型空间的亚稳态区域之间移动时出现的能量尖峰保持鲁棒。最后,我们将理论付诸实践,把增强的优化和采样方法应用于大晶格上的 transverse-field Ising 和 XXZ 模型,仅经过 200 次参数更新,就得到了具有极高精度的基态能量估计。

英文摘要:

Variational Monte Carlo (VMC) is an approach for computing ground-state wavefunctions that has recently become more powerful due to the introduction of neural network-based wavefunction parametrizations. However, efficiently training neural wavefunctions to converge to an energy minimum remains a difficult problem. In this work, we analyze optimization and sampling methods used in VMC and introduce alterations to improve their performance. First, based on theoretical convergence analysis in a noiseless setting, we motivate a new optimizer that we call the Rayleigh-Gauss-Newton method, which can improve upon gradient descent and natural gradient descent to achieve superlinear convergence at no more than twice the computational cost. Second, in order to realize this favorable comparison in the presence of stochastic noise, we analyze the effect of sampling error on VMC parameter updates and experimentally demonstrate that it can be reduced by the parallel tempering method. In particular, we demonstrate that RGN can be made robust to energy spikes that occur when the sampler moves between metastable regions of configuration space. Finally, putting theory into practice, we apply our enhanced optimization and sampling methods to the transverse-field Ising and XXZ models on large lattices, yielding ground-state energy estimates with remarkably high accuracy after just 200 parameter updates.

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。

↑