.png){kind=icon}
返回
Interaction decompositions for tensor network regression
.png){kind=icon}
OA
AI
DOI：10.1088/2632-2153/aca271.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
It is well known that tensor network regression models operate on an exponentially large feature space, but questions remain as to how effectively they are able to utilize this space. Using a polynomial featurization, we propose an interaction decomposition as a tool that can assess the relative importance of different regressors as a function of their polynomial degree. We apply this decomposition to tensor ring and tree tensor network models trained on the MNIST and Fashion MNIST datasets, and find that up to 75% of interaction degrees are contributing meaningfully to these models. We also introduce a new type of tensor network model that is explicitly trained on only a small subset of interaction degrees, and find that these models are able to match or even outperform the full models using only a fraction of the exponential feature space. This suggests that standard tensor network models utilize their polynomial regressors in an inefficient manner, with the lower degree terms being vastly under-utilized.
Keyword:
tensor regression
interaction decomposition
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
Molecular Modeling of the Structural and Dynamical Changes in Calcium Channel TRPV5 Induced by the African-Specific A563T Variation.png)
Biochemistry
OAAI
BiochemistryIF0
OAAI分享收藏分享收藏分享收藏分享收藏
查看更多内容