BUFF: Boosted Decision Tree based Ultra-Fast Flow matching
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929330019368960 |
|---|---|
| author | Jiang, Cheng Qian, Sitian Qu, Huilin |
| author_facet | Jiang, Cheng Qian, Sitian Qu, Huilin |
| contents | Tabular data stands out as one of the most frequently encountered types in high energy physics. Unlike commonly homogeneous data such as pixelated images, simulating high-dimensional tabular data and accurately capturing their correlations are often quite challenging, even with the most advanced architectures. Based on the findings that tree-based models surpass the performance of deep learning models for tasks specific to tabular data, we adopt the very recent generative modeling class named conditional flow matching and employ different techniques to integrate the usage of Gradient Boosted Trees. The performances are evaluated for various tasks on different analysis level with several public datasets. We demonstrate the training and inference time of most high-level simulation tasks can achieve speedup by orders of magnitude. The application can be extended to low-level feature simulation and conditioned generations with competitive performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_18219 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BUFF: Boosted Decision Tree based Ultra-Fast Flow matching Jiang, Cheng Qian, Sitian Qu, Huilin Instrumentation and Detectors Machine Learning High Energy Physics - Experiment High Energy Physics - Phenomenology Data Analysis, Statistics and Probability Tabular data stands out as one of the most frequently encountered types in high energy physics. Unlike commonly homogeneous data such as pixelated images, simulating high-dimensional tabular data and accurately capturing their correlations are often quite challenging, even with the most advanced architectures. Based on the findings that tree-based models surpass the performance of deep learning models for tasks specific to tabular data, we adopt the very recent generative modeling class named conditional flow matching and employ different techniques to integrate the usage of Gradient Boosted Trees. The performances are evaluated for various tasks on different analysis level with several public datasets. We demonstrate the training and inference time of most high-level simulation tasks can achieve speedup by orders of magnitude. The application can be extended to low-level feature simulation and conditioned generations with competitive performance. |
| title | BUFF: Boosted Decision Tree based Ultra-Fast Flow matching |
| topic | Instrumentation and Detectors Machine Learning High Energy Physics - Experiment High Energy Physics - Phenomenology Data Analysis, Statistics and Probability |
| url | https://arxiv.org/abs/2404.18219 |