题目: Generative Diffusion Models for Lattice Field Theory

报告人: 王凌霄 (IAS, Frankfurt)

时间: 2023年10月11日 (周三) 10:00

地点: 理科楼 B315

摘要:

This study delves into the connection between machine learning and lattice field theory by linking generative diffusion models (DMs) with stochastic quantization (SQ), from a stochastic differential equation(SDE) perspective. We show that DMs can be conceptualized by reversing a stochastic process driven by the Langevin equation, which then produces samples from an initial distribution to approximate the target distribution. In a toy model, we highlight the capability of DMs to learn effective actions. Furthermore, we demonstrate its feasibility to act as a global sampler for generating configurations in the two-dimensional $\phi^4$ quantum lattice field theory.

[Reference: ArXiv 2309.17082]

报告人简介:

Lingxiao Wang obtained his Ph.D. in Tsinghua University in 2020, during which he visited the University of Tokyo as joint Ph.D.. Later, he joined Frankfurt Institute for Advanced Studies (FIAS) as a postdoctoral researcher and concurrently served as an assistant researcher at Frankfurt University. His main research fields focus on the application of machine learning in exploring QCD physics, including the lattice quantum field theory(LQFT), the properties of dense nuclear matter and QCD phase transitions. In addition, he is also devoted to AI for Science from a multi-disciplinary perspective.