Stack operation of tensor networks
The tensor network, as a facterization of tensors, aims at performing the operations that are common for normal tensors, such as addition, contraction and stacking. However, due to its non-unique network structure, only the tensor network contraction is so far well defined. In this paper, we prop...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/160356 |
| _version_ | 1811689172304396288 |
|---|---|
| author | Zhang, Tianning Chen, Tianqi Li, Erping Yang, Bo Ang, L. K. |
| author2 | School of Physical and Mathematical Sciences |
| author_facet | School of Physical and Mathematical Sciences Zhang, Tianning Chen, Tianqi Li, Erping Yang, Bo Ang, L. K. |
| author_sort | Zhang, Tianning |
| collection | NTU |
| description | The tensor network, as a facterization of tensors, aims at performing the
operations that are common for normal tensors, such as addition, contraction
and stacking. However, due to its non-unique network structure, only the tensor
network contraction is so far well defined. In this paper, we propose a
mathematically rigorous definition for the tensor network stack approach, that
compress a large amount of tensor networks into a single one without changing
their structures and configurations. We illustrate the main ideas with the
matrix product states based machine learning as an example. Our results are
compared with the for loop and the efficient coding method on both CPU and GPU. |
| first_indexed | 2024-10-01T05:43:52Z |
| format | Journal Article |
| id | ntu-10356/160356 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:43:52Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1603562023-02-28T20:08:18Z Stack operation of tensor networks Zhang, Tianning Chen, Tianqi Li, Erping Yang, Bo Ang, L. K. School of Physical and Mathematical Sciences Science::Physics Tensor Network Stack Operation The tensor network, as a facterization of tensors, aims at performing the operations that are common for normal tensors, such as addition, contraction and stacking. However, due to its non-unique network structure, only the tensor network contraction is so far well defined. In this paper, we propose a mathematically rigorous definition for the tensor network stack approach, that compress a large amount of tensor networks into a single one without changing their structures and configurations. We illustrate the main ideas with the matrix product states based machine learning as an example. Our results are compared with the for loop and the efficient coding method on both CPU and GPU. Published version This work was supported by US Office of Naval Research Global (N62909-19-1-2047) and SUTD-ZJU Visiting Professor (VP 201303). 2022-07-20T06:06:01Z 2022-07-20T06:06:01Z 2022 Journal Article Zhang, T., Chen, T., Li, E., Yang, B. & Ang, L. K. (2022). Stack operation of tensor networks. Frontiers in Physics, 10, 906399-. https://dx.doi.org/10.3389/fphy.2022.906399 2296-424X https://hdl.handle.net/10356/160356 10.3389/fphy.2022.906399 2-s2.0-85130970420 10 906399 en Frontiers in Physics © 2022 Zhang, Chen, Li, Yang and Ang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. application/pdf |
| spellingShingle | Science::Physics Tensor Network Stack Operation Zhang, Tianning Chen, Tianqi Li, Erping Yang, Bo Ang, L. K. Stack operation of tensor networks |
| title | Stack operation of tensor networks |
| title_full | Stack operation of tensor networks |
| title_fullStr | Stack operation of tensor networks |
| title_full_unstemmed | Stack operation of tensor networks |
| title_short | Stack operation of tensor networks |
| title_sort | stack operation of tensor networks |
| topic | Science::Physics Tensor Network Stack Operation |
| url | https://hdl.handle.net/10356/160356 |
| work_keys_str_mv | AT zhangtianning stackoperationoftensornetworks AT chentianqi stackoperationoftensornetworks AT lierping stackoperationoftensornetworks AT yangbo stackoperationoftensornetworks AT anglk stackoperationoftensornetworks |