Tensor tree learns hidden relational structures in data to construct generative models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908297708175360 |
|---|---|
| author | Harada, Kenji Okubo, Tsuyoshi Kawashima, Naoki |
| author_facet | Harada, Kenji Okubo, Tsuyoshi Kawashima, Naoki |
| contents | Based on the tensor tree network with the Born machine framework, we propose a general method for constructing a generative model by expressing the target distribution function as the amplitude of the quantum wave function represented by a tensor tree. The key idea is dynamically optimizing the tree structure that minimizes the bond mutual information. The proposed method offers enhanced performance and uncovers hidden relational structures in the target data. We illustrate potential practical applications with four examples: (i) random patterns, (ii) QMNIST handwritten digits, (iii) Bayesian networks, and (iv) the pattern of stock price fluctuation pattern in S&P500. In (i) and (ii), the strongly correlated variables were concentrated near the center of the network; in (iii), the causality pattern was identified; and in (iv), a structure corresponding to the eleven sectors emerged. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10669 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Tensor tree learns hidden relational structures in data to construct generative models Harada, Kenji Okubo, Tsuyoshi Kawashima, Naoki Machine Learning Statistical Mechanics Artificial Intelligence Quantum Physics Based on the tensor tree network with the Born machine framework, we propose a general method for constructing a generative model by expressing the target distribution function as the amplitude of the quantum wave function represented by a tensor tree. The key idea is dynamically optimizing the tree structure that minimizes the bond mutual information. The proposed method offers enhanced performance and uncovers hidden relational structures in the target data. We illustrate potential practical applications with four examples: (i) random patterns, (ii) QMNIST handwritten digits, (iii) Bayesian networks, and (iv) the pattern of stock price fluctuation pattern in S&P500. In (i) and (ii), the strongly correlated variables were concentrated near the center of the network; in (iii), the causality pattern was identified; and in (iv), a structure corresponding to the eleven sectors emerged. |
| title | Tensor tree learns hidden relational structures in data to construct generative models |
| topic | Machine Learning Statistical Mechanics Artificial Intelligence Quantum Physics |
| url | https://arxiv.org/abs/2408.10669 |