Active Learning for the Optimal Design of Multinomial Classification in Physics

TL;DR

This paper explores active learning techniques to optimize experimental design in physics, achieving high accuracy with minimal labeled samples in quantum information retrieval and phase boundary prediction.

Contribution

It demonstrates the effectiveness of active learning in physics experiments, reducing labeling costs while maintaining high classification accuracy.

Findings

Achieved 99% correct rate with less than 2% labeled samples.

Reduced experimental costs by applying active learning in physics.

Validated approach in quantum information and many-body physics applications.

Abstract

Optimal design for model training is a critical topic in machine learning. Active Learning aims at obtaining improved models by querying samples with maximum uncertainty according to the estimation model for artificially labeling; this has the additional advantage of achieving successful performances with a reduced number of labeled samples. We analyze its capability as an assistant for the design of experiments, extracting maximum information for learning with the minimal cost in fidelity loss, or reducing total operation costs of labeling in the laboratory. We present two typical applications as quantum information retrieval in qutrits and phase boundary prediction in many-body physics. For an equivalent multinomial classification problem, we achieve the correct rate of 99% with less than 2% samples labeled. We reckon that active-learning-inspired physics experiments will remarkably save budget without loss of accuracy.