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...
Gardado en:
| Principais autores: | , , , |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado: |
Nature Portfolio
2026-07-01
|
| Series: | Nature Communications |
| Acceso en liña: | https://doi.org/10.1038/s41467-026-75439-1 |
| Tags: |
Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!
|