TensorKrowch: Smooth integration of tensor networks in machine learning

被引:0
作者
Monturiol, Jose Ramon Pareja [1 ,2 ]
Perez-Garcia, David [1 ,2 ]
Pozas-Kerstjens, Alejandro [2 ]
机构
[1] Univ Complutense Madrid, Dept Anal Matemat, Madrid 28040, Spain
[2] CSIC UAM UC3M UCM, Inst Ciencias Matemat, Madrid 28049, Spain
关键词
DECOMPOSITION; STATES;
D O I
暂无
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Tensor networks are factorizations of high-dimensional tensors into networks of smaller tensors. They have applications in physics and mathematics, and recently have been proposed as promising machine learning architectures. To ease the integration of tensor networks in machine learning pipelines, we introduce TensorKrowch, an open source Python library built on top of PyTorch. Providing a user-friendly interface, TensorKrowch allows users to construct any tensor network, train it, and integrate it as a layer in more intricate deep learning models. In this paper, we describe the main functionality and basic usage of TensorKrowch, and provide technical details on its building blocks and the optimizations performed to achieve efficient operation.
引用
收藏
页码:1 / 20
页数:20
相关论文
共 62 条
[1]   The minimal canonical form of a tensor network [J].
Acuaviva, Arturo ;
Makam, Visu ;
Nieuwboer, Harold ;
Perez-Garcia, David ;
Sittner, Friedrich ;
Walter, Michael .
2023 IEEE 64TH ANNUAL SYMPOSIUM ON FOUNDATIONS OF COMPUTER SCIENCE, FOCS, 2023, :328-362
[2]  
Aizpurua B, 2024, Arxiv, DOI [arXiv:2401.00867, arXiv:2401.00867]
[3]   Hand-waving and interpretive dance: an introductory course on tensor networks [J].
Bridgeman, Jacob C. ;
Chubb, Christopher T. .
JOURNAL OF PHYSICS A-MATHEMATICAL AND THEORETICAL, 2017, 50 (22)
[4]   Tree tensor networks for generative modeling [J].
Cheng, Song ;
Wang, Lei ;
Xiang, Tao ;
Zhang, Pan .
PHYSICAL REVIEW B, 2019, 99 (15)
[5]   Matrix product states and projected entangled pair states: Concepts, symmetries, theorems [J].
Cirac, J. Ignacio ;
Perez-Garcia, David ;
Schuch, Norbert ;
Verstraete, Frank .
REVIEWS OF MODERN PHYSICS, 2021, 93 (04)
[6]   Complexity of tensor calculus [J].
Damm, C ;
Holzer, M ;
McKenzie, P .
COMPUTATIONAL COMPLEXITY, 2002, 11 (1-2) :54-89
[7]   Parallel cross interpolation for high-precision calculation of high-dimensional integrals [J].
Dolgov, Sergey ;
Savostyanov, Dmitry .
COMPUTER PHYSICS COMMUNICATIONS, 2020, 246
[8]  
Dolgov SV, 2022, Arxiv, DOI arXiv:2209.03756
[9]   Algorithms for entanglement renormalization [J].
Evenbly, G. ;
Vidal, G. .
PHYSICAL REVIEW B, 2009, 79 (14)
[10]   FINITELY CORRELATED STATES ON QUANTUM SPIN CHAINS [J].
FANNES, M ;
NACHTERGAELE, B ;
WERNER, RF .
COMMUNICATIONS IN MATHEMATICAL PHYSICS, 1992, 144 (03) :443-490