TensorNetwork: A Library for Physics and Machine Learning

TL;DR

TensorNetwork is an open source library that facilitates tensor network algorithms, originally for physics but now also applied in machine learning, demonstrating versatility across disciplines.

Contribution

The paper introduces TensorNetwork, a versatile library enabling efficient tensor network computations for physics and machine learning applications.

Findings

Supports quantum many-body physics simulations

Applied successfully in machine learning tasks

Open source and user-friendly API

Abstract

TensorNetwork is an open source library for implementing tensor network algorithms. Tensor networks are sparse data structures originally designed for simulating quantum many-body physics, but are currently also applied in a number of other research areas, including machine learning. We demonstrate the use of the API with applications both physics and machine learning, with details appearing in companion papers.