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...
-д хадгалсан:
| Үндсэн зохиолчид: | , , , |
|---|---|
| Формат: | Artigo |
| Хэл сонгох: | Inglês |
| Хэвлэсэн: |
Nature Portfolio
2026-07-01
|
| Цуврал: | Nature Communications |
| Онлайн хандалт: | https://doi.org/10.1038/s41467-026-75439-1 |
| Шошгууд: |
Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!
|