PulseAugur
中
实时 09:24:31
English(EN) Is Variational Monte Carlo Robust? Sharp Moment Thresholds and Heavy-tailed Stochastic Optimization

新的PS-Clip-VMC算法增强了随机优化的鲁棒性

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员开发了一种新的变分蒙特卡洛（VMC）算法变体，名为PS-Clip-VMC，旨在提高随机优化的鲁棒性。这种新方法解决了估计量局部能量和梯度通常是重尾且缺乏高阶矩的问题，这会阻碍收敛。PS-Clip-VMC通过裁剪这些随机变量来实现期望和高概率下的收敛。在原子系统上使用FermiNet进行的初步实验表明，与标准的VMC方法相比，鲁棒性有了显著提高。 AI

影响 引入了一种更鲁棒的优化技术，可以提高科学计算中复杂模型的训练稳定性。

排序理由 详细介绍新算法及其理论特性的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的PS-Clip-VMC算法增强了随机优化的鲁棒性

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Philipp Grohs, Davide Nobile ·

    Is Variational Monte Carlo Robust? Sharp Moment Thresholds and Heavy-tailed Stochastic Optimization

    arXiv:2606.26009v1 Announce Type: new Abstract: Variational Monte Carlo (VMC) is a central algorithm in electronic structure theory and has gained renewed importance through modern neural-network ans\"atze such as FermiNet. At its core, VMC seeks ground states by minimizing the R…

  2. arXiv cs.LG TIER_1 English(EN) · Davide Nobile ·

    Is Variational Monte Carlo Robust? Sharp Moment Thresholds and Heavy-tailed Stochastic Optimization

    Variational Monte Carlo (VMC) is a central algorithm in electronic structure theory and has gained renewed importance through modern neural-network ansätze such as FermiNet. At its core, VMC seeks ground states by minimizing the Rayleigh quotient by stochastic optimization. In th…

相关话题