Improving the performance of weak supervision searches using data augmentation

TL;DR

This paper introduces physics-inspired data augmentation techniques to improve weak supervision training, allowing neural networks to learn effectively from less data by increasing diversity and size of training datasets.

Contribution

The study proposes novel physics-inspired data augmentation methods, such as $p_{T}$ smearing and jet rotation, to enhance weak supervision performance in neural network training.

Findings

Data augmentation significantly improves weak supervision results.

Neural networks learn more efficiently with augmented data.

Performance gains enable training with less data.

Abstract

Weak supervision combines the advantages of training on real data with the ability to exploit signal properties. However, training a neural network using weak supervision often requires an excessive amount of signal data, which severely limits its practical applicability. In this study, we propose addressing this limitation through data augmentation, increasing the training data's size and diversity. Specifically, we focus on physics-inspired data augmentation methods, such as $p_{\text{T}}$ smearing and jet rotation. Our results demonstrate that data augmentation can significantly enhance the performance of weak supervision, enabling neural networks to learn efficiently from substantially less data.