BNEM: A Boltzmann Sampler Based on Bootstrapped Noised Energy Matching

ArXi:2409.09787v5 Announce Type: replace Developing an efficient sampler capable of generating independent and identically distributed (IID) samples from a Boltzmann distribution is a crucial challenge in scientific research, e.g. molecular dynamics. In this work, we intend to learn neural samplers given energy functions instead of data sampled from the Boltzmann distribution. By learning the energies of the noised data, we propose a diffusion-based sampler, Noised Energy Matching, which theoretically has lower variance and complexity compared to related works.