Approximating the total variation distance between spin systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911004226486272 |
|---|---|
| author | Feng, Weiming Liu, Hongyang Yang, Minji |
| author_facet | Feng, Weiming Liu, Hongyang Yang, Minji |
| contents | Spin systems form an important class of undirected graphical models. For two Gibbs distributions $μ$ and $ν$ induced by two spin systems on the same graph $G = (V, E)$, we study the problem of approximating the total variation distance $d_{TV}(μ,ν)$ with an $ε$-relative error. We propose a new reduction that connects the problem of approximating the TV-distance to sampling and approximate counting. Our applications include the hardcore model and the antiferromagnetic Ising model in the uniqueness regime, the ferromagnetic Ising model, and the general Ising model satisfying the spectral condition.
Additionally, we explore the computational complexity of approximating the total variation distance $d_{TV}(μ_S,ν_S)$ between two marginal distributions on an arbitrary subset $S \subseteq V$. We prove that this problem remains hard even when both $μ$ and $ν$ admit polynomial-time sampling and approximate counting algorithms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_05437 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Approximating the total variation distance between spin systems Feng, Weiming Liu, Hongyang Yang, Minji Data Structures and Algorithms Machine Learning Probability Spin systems form an important class of undirected graphical models. For two Gibbs distributions $μ$ and $ν$ induced by two spin systems on the same graph $G = (V, E)$, we study the problem of approximating the total variation distance $d_{TV}(μ,ν)$ with an $ε$-relative error. We propose a new reduction that connects the problem of approximating the TV-distance to sampling and approximate counting. Our applications include the hardcore model and the antiferromagnetic Ising model in the uniqueness regime, the ferromagnetic Ising model, and the general Ising model satisfying the spectral condition. Additionally, we explore the computational complexity of approximating the total variation distance $d_{TV}(μ_S,ν_S)$ between two marginal distributions on an arbitrary subset $S \subseteq V$. We prove that this problem remains hard even when both $μ$ and $ν$ admit polynomial-time sampling and approximate counting algorithms. |
| title | Approximating the total variation distance between spin systems |
| topic | Data Structures and Algorithms Machine Learning Probability |
| url | https://arxiv.org/abs/2502.05437 |