Estimation of the pseudoscalar glueball mass based on a modified Transformer

TL;DR

This paper introduces a modified Transformer model for estimating pseudoscalar glueball mass in lattice QCD, demonstrating improved accuracy and adaptability over traditional methods and previous neural networks.

Contribution

The paper presents a novel Transformer-based approach with positional encoding for mass estimation, enhancing accuracy and input flexibility in lattice QCD applications.

Findings

Modified Transformer outperforms least squares in accuracy.

Model handles variable input lengths effectively.

Enhanced adaptability over previous neural network methods.

Abstract

A modified Transformer model is introduced for estimating the mass of pseudoscalar glueball in lattice QCD. The model takes as input a sequence of floating-point numbers with lengths ranging from 30 to 35 and produces a two-dimensional vector output. It integrates floating-point embeddings and positional encoding, and is trained using binary cross-entropy loss. The paper provides a detailed description of the model's components and training methods, and compares the performance of the traditional least squares method, the previously used deep neural network, and the modified Transformer in mass estimation. The results show that the modified Transformer model achieves greater accuracy in mass estimation than the traditional least squares method. Additionally, compared to the deep neural network, this model utilizes positional encoding and can handle input sequences of varying lengths, offering enhanced adaptability.