Classifying Topological Charge in SU(3) Yang-Mills Theory with Machine Learning
This work addresses a specific computational challenge in theoretical physics, offering an incremental improvement in efficiency for analyzing quantum gauge configurations.
The paper tackles the problem of identifying topological charge in SU(3) Yang-Mills theory using machine learning, achieving over 99% accuracy in predicting topological charge from small flow time data with high robustness to parameter changes.
We apply a machine learning technique for identifying the topological charge of quantum gauge configurations in four-dimensional SU(3) Yang-Mills theory. The topological charge density measured on the original and smoothed gauge configurations with and without dimensional reduction is used as inputs for the neural networks (NN) with and without convolutional layers. The gradient flow is used for the smoothing of the gauge field. We find that the topological charge determined at a large flow time can be predicted with high accuracy from the data at small flow times by the trained NN; for example, the accuracy exceeds $99\%$ with the data at $t/a^2\le0.3$. High robustness against the change of simulation parameters is also confirmed with a fixed physical volume. We find that the best performance is obtained when the spatial coordinates of the topological charge density are fully integrated out in preprocessing, which implies that our convolutional NN does not find characteristic structures in multi-dimensional space relevant for the determination of the topological charge.