tn4ml: Tensor Network Training and Customization for Machine Learning

TL;DR

The paper presents tn4ml, a new library that integrates Tensor Networks into machine learning workflows, enabling flexible data embedding, optimization, and customization for various learning tasks.

Contribution

It introduces a user-friendly library that facilitates the application of Tensor Networks in machine learning pipelines, with customizable components for improved performance.

Findings

Demonstrates supervised learning on tabular data using tn4ml.

Shows unsupervised learning on image datasets with Tensor Networks.

Analyzes the impact of pipeline customization on performance.

Abstract

Tensor Networks have emerged as a prominent alternative to neural networks for addressing Machine Learning challenges in foundational sciences, paving the way for their applications to real-life problems. This paper introduces tn4ml, a novel library designed to seamlessly integrate Tensor Networks into optimization pipelines for Machine Learning tasks. Inspired by existing Machine Learning frameworks, the library offers a user-friendly structure with modules for data embedding, objective function definition, and model training using diverse optimization strategies. We demonstrate its versatility through two examples: supervised learning on tabular data and unsupervised learning on an image dataset. Additionally, we analyze how customizing the parts of the Machine Learning pipeline for Tensor Networks influences performance metrics.