arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.00828cs.LGhep-latstat.ML
收藏

基于神经算子流的量子场论多格点采样

Multi-Lattice Sampling of Quantum Field Theories via Neural Operator-based Flows

University of Geneva(日内瓦大学)

Bálint Máté, François Fleuret

AI总结:

针对从玻尔兹曼分布采样格点场构型的问题,提出基于神经算子的时间依赖流,通过离散化为向量场诱导连续归一化流,在二维$ϕ^4$理论验证其对未训练格点的泛化性,且小格点预训练可加速目标格点训练。

摘要:

我们研究从与某作用量对应的玻尔兹曼分布中采样格点场构型的问题。由于这类密度是底层泛函密度的近似,我们将该任务视为算子学习的一个实例。我们提出近似一个时间依赖的神经算子,其时间积分提供自由理论与目标理论泛函分布之间的映射。一旦选定特定格点,该神经算子可离散化为有限维时间依赖向量场,进而诱导所选格点上有限维分布之间的连续归一化流。此流可被训练为所选格点上离散化自由理论与目标理论之间的微分同胚,且通过构造,可在不同时空离散化下评估。我们在二维$ϕ^4$理论上实验验证该方案,探索此类基于算子的流架构对未训练格点尺寸的泛化程度,并表明在小格点上预训练可加速直接在目标格点尺寸上的训练。

英文摘要:

We consider the problem of sampling lattice field configurations on a lattice from the Boltzmann distribution corresponding to some action. Since such densities arise as approximationw of an underlying functional density, we frame the task as an instance of operator learning. We propose to approximate a time-dependent neural operator whose time integral provides a mapping between the functional distributions of the free and target theories. Once a particular lattice is chosen, the neural operator can be discretized to a finite-dimensional, time-dependent vector field which in turn induces a continuous normalizing flow between finite dimensional distributions over the chosen lattice. This flow can then be trained to be a diffeormorphism between the discretized free and target theories on the chosen lattice, and, by construction, can be evaluated on different discretizations of spacetime. We experimentally validate the proposal on the 2-dimensional $ϕ^4$-theory to explore to what extent such operator-based flow architectures generalize to lattice sizes they were not trained on, and show that pretraining on smaller lattices can lead to a speedup over training directly on the target lattice size.

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。

↑