EUVIMEDEUVIMED entdecken
Crossref

Renormalization Group Guided Tensor Network Structure Search

Maolin Wang, Bowen Yu, Sheng Zhang, Linjie Mi, Wanyu Wang, Yiqi Wang, Pengyue Jia, Xuetao Wei, Zenglin Xu, Ruocheng Guo, Xiangyu Zhao

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (31) · 26346-26354

DOI: 10.1609/aaai.v40i31.39840 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Maolin Wang und 10 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Tensor network structure search (TN-SS) aims to automatically discover optimal network topologies and rank configurations for efficient tensor decomposition in high-dimensional data representation. Despite recent advances, existing TN-SS methods face significant limitations in computational tractability, structure adaptivity, and optimization robustness across diverse tensor characteristics. They struggle with three key challenges: single-scale optimization missing multi-scale structures, discrete search spaces hindering smooth structure evolution, and separated structure-parameter optimization causing computational inefficiency. We propose RGTN (Renormalization Group guided Tensor Network search), a physics-inspired framework transforming TN-SS via multi-scale renormalization group flows. Unlike fixed-scale discrete search methods, RGTN uses dynamic scale-transformation for continuous structure evolution across resolutions. Its core innovation includes learnable edge gates for optimization-stage topology modification and intelligent proposals based on physical quantities like node tension measuring local stress, and edge information flow quantifying connectivity importance. Starting from low-complexity coarse scales and refining to finer ones, RGTN finds compact structures while escaping local minima via scale-induced perturbations. Extensive experiments on light field data, high-order synthetic tensors, and video completion tasks show RGTN achieves state-of-the-art compression ratios and runs 4-600 times faster than existing methods, validating the effectiveness of our physics-inspired approach.

Zitieren

APA

Wang, M., Yu, B., Zhang, S., Mi, L., Wang, W., Wang, Y., Jia, P., Wei, X., Xu, Z., Guo, R., & Zhao, X. (2026). Renormalization Group Guided Tensor Network Structure Search. Proceedings of the AAAI Conference on Artificial Intelligence, 40(31), 26346-26354. https://doi.org/10.1609/aaai.v40i31.39840

Vancouver

Wang M, Yu B, Zhang S, Mi L, Wang W, Wang Y, et al. Renormalization Group Guided Tensor Network Structure Search. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(31):26346-26354. doi:10.1609/aaai.v40i31.39840

BibTeX
@article{Wang2026,
  author = {Wang, Maolin and Yu, Bowen and Zhang, Sheng and Mi, Linjie and Wang, Wanyu and Wang, Yiqi and Jia, Pengyue and Wei, Xuetao and Xu, Zenglin and Guo, Ruocheng and Zhao, Xiangyu},
  title = {Renormalization Group Guided Tensor Network Structure Search},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {31},
  pages = {26346--26354},
  doi = {10.1609/aaai.v40i31.39840}
}
Kostenlos starten →