Residual matrix product state for machine learning
SciPost Physics · 02.06.2023 · 14 (6)
DOI: 10.21468/scipostphys.14.6.142 ↗Kurz gefasst
Fachartikel in der Zeitschrift SciPost Physics, online erschienen am 02.06.2023. Verfasst von Ye-Ming Meng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beijing Municipal Natural Science Foundation, Capital Normal University, National Natural Science Foundation of China.
Abstract (Originalsprache)
Tensor network, which originates from quantum physics, is emerging as an efficient tool for classical and quantum machine learning. Nevertheless, there still exists a considerable accuracy gap between tensor network and the sophisticated neural network models for classical machine learning. In this work, we combine the ideas of matrix product state (MPS), the simplest tensor network structure, and residual neural network and propose the residual matrix product state (ResMPS). The ResMPS can be treated as a network where its layers map the "hidden" features to the outputs (e.g., classifications), and the variational parameters of the layers are the functions of the features of the samples (e.g., pixels of images). This is different from neural network, where the layers map feed-forwardly the features to the output. The ResMPS can equip with the non-linear activations and dropout layers, and outperforms the state-of-the-art tensor network models in terms of efficiency, stability, and expression power. Besides, ResMPS is interpretable from the perspective of polynomial expansion, where the factorization and exponential machines naturally emerge. Our work contributes to connecting and hybridizing neural and tensor networks, which is crucial to further enhance our understanding of the working mechanisms and improve the performance of both models.
Förderung
- Beijing Municipal Natural Science Foundation
- Capital Normal University
- National Natural Science Foundation of China
- Natural Science Foundation of Zhejiang Province
Zitieren
APA
Meng, Y., Zhang, J., Zhang, P., Gao, C., & Ran, S. (2023). Residual matrix product state for machine learning. SciPost Physics, 14(6). https://doi.org/10.21468/scipostphys.14.6.142
Vancouver
Meng Y, Zhang J, Zhang P, Gao C, Ran S. Residual matrix product state for machine learning. SciPost Physics. 2023;14(6). doi:10.21468/scipostphys.14.6.142
BibTeX
@article{Meng2023,
author = {Meng, Ye-Ming and Zhang, Jing and Zhang, Peng and Gao, Chao and Ran, Shi-Ju},
title = {Residual matrix product state for machine learning},
journal = {SciPost Physics},
year = {2023},
volume = {14},
number = {6},
doi = {10.21468/scipostphys.14.6.142}
}
EUVIMED