26 July 2026 to 1 August 2026
University of Maryland, College Park
US/Eastern timezone

AI/ML-inspired RMHMC kernels--CPN model study

28 Jul 2026, 16:30
20m
Crossland (Adele H. Stamp Student Union)

Crossland

Adele H. Stamp Student Union

3972 Campus Dr, College Park, MD 20742
Poster presentation Software development and machines Software development and machines

Speaker

Nobuyuki Matsumoto (Boston University)

Description

Riemannian manifold HMC (RMHMC), following the basic idea of Fourier acceleration, has been studied as a viable algorithm toward mitigating critical slowing down. In fact, by using multilevel integration, the algorithmic overhead becomes additive to the fermionic inversion cost that dominates in production runs, especially with domain-wall fermions. Given the rapid development of AI/ML, we explore constructing the kernel as a neural network. Using the CPN model as a testbed, we report on the results from representative kernels. We further report on software development towards migrating to QCD.

Authors

Ryan Abbott (Columbia University) Peter Boyle Luchang Jin (Univeristy of Connecticut) Christopher Kelly Christoph Lehner (Universität Regensburg) Nobuyuki Matsumoto (Boston University)

Presentation materials