Improving the performance of weak supervision searches using data augmentation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917875299647488 |
|---|---|
| author | Chen, Zong-En Chiang, Cheng-Wei Hsieh, Feng-Yang |
| author_facet | Chen, Zong-En Chiang, Cheng-Wei Hsieh, Feng-Yang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_00198 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving the performance of weak supervision searches using data augmentation Chen, Zong-En Chiang, Cheng-Wei Hsieh, Feng-Yang High Energy Physics - Phenomenology Machine Learning High Energy Physics - Experiment 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. |
| title | Improving the performance of weak supervision searches using data augmentation |
| topic | High Energy Physics - Phenomenology Machine Learning High Energy Physics - Experiment |
| url | https://arxiv.org/abs/2412.00198 |