# Machine learning as an improved estimator for magnetization curve and spin gap

## TL;DR

This paper introduces a machine learning method that accurately estimates magnetization curves and spin gaps in quantum spin systems from limited numerical data, aiding the study of magnetic materials and spin-liquid states.

## Contribution

A novel machine learning algorithm that improves estimation of magnetization and spin gaps from poor data, validated on solvable models and applied to kagome antiferromagnets.

## Key findings

- Accurately estimates critical fields and exponents.
- Consistent with larger-scale DMRG results.
- Identifies whether the spin gap is zero or finite.

## Abstract

The magnetization process is a very important probe to study magnetic materials, particularly in search of spin-liquid states in quantum spin systems. Regrettably, however, progress of the theoretical analysis has been unsatisfactory, mostly because it is hard to obtain sufficient numerical data to support the theory. Here we propose a machine-learning algorithm that produces the magnetization curve and the spin gap well out of poor numerical data. The plateau magnetization, its critical field and the critical exponent are estimated accurately. One of the hyperparameters identifies by its score whether the spin gap in the thermodynamic limit is zero or finite. After checking the validity for exactly solvable one-dimensional models we apply our algorithm to the kagome antiferromagnet. The magnetization curve that we obtain from the exact-diagonalization data with 36 spins is consistent with the DMRG results with 132 spins. We estimate the spin gap in the thermodynamic limit at a very small but finite value.