Discrete distributions are learnable from metastable samples
Abstract Physically motivated stochastic dynamics are widely used to sample from high-dimensional distributions. However, such samplers often get trapped in metastable states, approximately sampling from a distribution that differs significantly from the desired stationary state. We rigorously show...
Wedi'i Gadw mewn:
| Prif Awduron: | , , , |
|---|---|
| Fformat: | Artigo |
| Iaith: | Inglês |
| Cyhoeddwyd: |
Nature Portfolio
2026-07-01
|
| Cyfres: | Nature Communications |
| Mynediad Ar-lein: | https://doi.org/10.1038/s41467-026-75439-1 |
| Tagiau: |
Dim Tagiau, Byddwch y cyntaf i dagio'r cofnod hwn!
|