TensorKrowch: Smooth integration of tensor networks in machine learning
arXiv:2306.08595 · doi:10.22331/q-2024-06-11-1364
Abstract
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.
arXiv comment20 pages, 2 figures. The TensorKrowch GitHub repository is in https://github.com/joserapa98/tensorkrowch and the TensorKrowch documentation is in https://joserapa98.github.io/tensorkrowch. V3: Accepted version, corrected acknowledgments
References in corpus (28)
- The density-matrix renormalization group
- Efficient classical simulation of slightly entangled quantum computations
- A Practical Introduction to Tensor Networks: Matrix Product States and Projected Entangled Pair States
- Tensor Decomposition for Signal Processing and Machine Learning
- Entanglement renormalization
- A class of quantum many-body states that can be efficiently simulated
- Matrix Product States and Projected Entangled Pair States: Concepts, Symmetries, and Theorems
- Criticality, the area law, and the computational power of PEPS
- Classical simulation of quantum many-body systems with a tree tensor network
- Hand-waving and Interpretive Dance: An Introductory Course on Tensor Networks
- Matrix product operator representations
- Algorithms for entanglement renormalization
- Variational optimization algorithms for uniform matrix product states
- Simulation of two-dimensional quantum systems using a tree tensor network that exploits the entropic area law
- Simulating Strongly Correlated Quantum Systems with Tree Tensor Networks
- Hyper-optimized tensor network contraction
- Solving the sampling problem of the Sycamore quantum circuits
- Tree Tensor Networks for Generative Modeling
- Machine Learning by Unitary Tensor Network of Hierarchical Tree Structure
- Parallel cross interpolation for high-precision calculation of high-dimensional integrals
- Isometric Tensor Network representation of string-net liquids
- Efficient Simulation of Dynamics in Two-Dimensional Quantum Spin Systems with Isometric Tensor Networks
- Matrix product states approaches to operator spreading in ergodic quantum systems
- Symmetric Tensor Networks for Generative Modeling and Constrained Combinatorial Optimization
- The minimal canonical form of a tensor network
- Explainable Natural Language Processing with Matrix Product States
- Tensor product approach to modelling epidemics on networks
- RosneT: A Block Tensor Algebra Library for Out-of-Core Quantum Computing Simulation