Flow Annealed Importance Sampling Bootstrap meets Differentiable Particle Physics
This work addresses a computational bottleneck for physicists by providing a more efficient method for data simulation, though it appears incremental as it builds on existing surrogate model techniques.
The paper tackles the problem of generating simulated data samples from complex distributions in high-energy physics by using Flow Annealed Importance Sampling Bootstrap (FAB), which improves sampling efficiency with fewer target evaluations in high dimensions compared to other methods.
High-energy physics requires the generation of large numbers of simulated data samples from complex but analytically tractable distributions called matrix elements. Surrogate models, such as normalizing flows, are gaining popularity for this task due to their computational efficiency. We adopt an approach based on Flow Annealed importance sampling Bootstrap (FAB) that evaluates the differentiable target density during training and helps avoid the costly generation of training data in advance. We show that FAB reaches higher sampling efficiency with fewer target evaluations in high dimensions in comparison to other methods.