NeuMC -- a package for neural sampling for lattice field theories
This work addresses the need for improved sampling methods in lattice field theories, but it is incremental as it primarily provides a software tool without demonstrating new algorithmic breakthroughs.
The authors tackled the challenge of Monte-Carlo simulations in lattice field theories by developing the NeuMC software package, which facilitates the creation of neural samplers based on normalizing flows for two-dimensional field theories, though no concrete numerical results are provided.
We present the \texttt{NeuMC} software package, based on \pytorch, aimed at facilitating the research on neural samplers in lattice field theories. Neural samplers based on normalizing flows are becoming increasingly popular in the context of Monte-Carlo simulations as they can effectively approximate target probability distributions, possibly alleviating some shortcomings of the Markov chain Monte-Carlo methods. Our package provides tools to create such samplers for two-dimensional field theories.