tn4ml: Tensor Network Training and Customization for Machine Learning
This provides a tool for researchers and practitioners in foundational sciences to apply Tensor Networks to real-life machine learning problems, though it is incremental as it builds on existing frameworks.
The paper introduces tn4ml, a library for integrating Tensor Networks into machine learning optimization pipelines, demonstrating its versatility through supervised learning on tabular data and unsupervised learning on an image dataset, with analysis of how customization affects performance metrics.
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.