TensorKrowch: Smooth integration of tensor networks in machine learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914831470166016 |
|---|---|
| author | Monturiol, José Ramón Pareja Pérez-García, David Pozas-Kerstjens, Alejandro |
| author_facet | Monturiol, José Ramón Pareja Pérez-García, David Pozas-Kerstjens, Alejandro |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_08595 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | TensorKrowch: Smooth integration of tensor networks in machine learning Monturiol, José Ramón Pareja Pérez-García, David Pozas-Kerstjens, Alejandro Machine Learning Statistical Mechanics Strongly Correlated Electrons Quantum Physics 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. |
| title | TensorKrowch: Smooth integration of tensor networks in machine learning |
| topic | Machine Learning Statistical Mechanics Strongly Correlated Electrons Quantum Physics |
| url | https://arxiv.org/abs/2306.08595 |