.png){kind=icon}
返回
Mutual information scaling for tensor network machine learning
.png){kind=icon}
OA
AI
DOI：10.1088/2632-2153/ac44a9.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Tensor networks have emerged as promising tools for machine learning, inspired by their widespread use as variational ansatze in quantum many-body physics. It is well known that the success of a given tensor network ansatz depends in part on how well it can reproduce the underlying entanglement structure of the target state, with different network designs favoring different scaling patterns. We demonstrate here how a related correlation analysis can be applied to tensor network machine learning, and explore whether classical data possess correlation scaling patterns similar to those found in quantum states, which might indicate the best network to use for a given dataset. We utilize mutual information (MI) as measure of correlations in classical data, and show that it can serve as a lower-bound on the entanglement needed for a probabilistic tensor network classifier. We then develop a logistic regression algorithm to estimate the MI between bipartitions of data features, and verify its accuracy on a set of Gaussian distributions designed to mimic different correlation patterns. Using this algorithm, we characterize the scaling patterns in the Modified National Institute of Standards and Technology and Tiny Images datasets, and find clear evidence of boundary-law scaling in the latter. This quantum-inspired classical analysis offers insight into the design of tensor networks that are best suited for specific learning tasks.
Keyword:
area law
mutual information
tensor network machine learning
期刊
M
IF:
4.6
论文数:
1.1K
被引数:
3.4K
机构
引用论文
Towards a cyanobacterial biorefinery: Carbohydrate fingerprint, biocomposition and enzymatic hydrolysis of Nostoc biomass走向蓝细菌生物精炼厂: Nostoc生物质的碳水化合物指纹，生物组成和酶促水解
PREAI
分享收藏分享收藏Matrix product states, projected entangled pair states, and variational renormalization group methods for quantum spin systems量子自旋系统的矩阵乘积态，投影纠缠态和变分重归一化组方法.png)
ADVANCES IN PHYSICSOAAI
ADVANCES IN PHYSICSIF13.8
OAAI分享收藏Efficient simulation of infinite tree tensor network states on the Bethe latticePHYSICAL REVIEW B
OAAI
PHYSICAL REVIEW BIF3.7
OAAI分享收藏
查看更多内容