BUFF: Boosted Decision Tree based Ultra-Fast Flow matching

TL;DR

This paper introduces BUFF, a method that leverages gradient boosted trees within a conditional flow matching framework to achieve ultra-fast and accurate simulation of high-dimensional tabular data, significantly improving speed over traditional methods.

Contribution

The paper presents a novel integration of gradient boosted trees with conditional flow matching for efficient tabular data simulation, outperforming existing deep learning approaches in speed.

Findings

Training and inference times are reduced by orders of magnitude.

The method achieves competitive performance in low-level feature simulation.

Applicable to various datasets and analysis levels.

Abstract

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.