DCTRGAN: Improving the Precision of Generative Models with Reweighting
This incremental refinement method addresses precision issues in generative models, particularly for high energy physics applications and other domains.
The paper tackles the problem of improving the fidelity of generative models like GANs by introducing a post-hoc reweighting correction based on the DCTR protocol, showing that weighted examples significantly enhance accuracy without major statistical loss.
Significant advances in deep learning have led to more widely used and precise neural network-based generative models such as Generative Adversarial Networks (GANs). We introduce a post-hoc correction to deep generative models to further improve their fidelity, based on the Deep neural networks using the Classification for Tuning and Reweighting (DCTR) protocol. The correction takes the form of a reweighting function that can be applied to generated examples when making predictions from the simulation. We illustrate this approach using GANs trained on standard multimodal probability densities as well as calorimeter simulations from high energy physics. We show that the weighted GAN examples significantly improve the accuracy of the generated samples without a large loss in statistical power. This approach could be applied to any generative model and is a promising refinement method for high energy physics applications and beyond.