Implicit Generative Prior for Bayesian Neural Networks

arXiv:2404.18008v1 Announce Type: new
Abstract: Predictive uncertainty quantification is crucial for reliable decision-making in various applied domains. Bayesian neural networks offer a powerful framework for this task. However, defining meaningful priors and ensuring computational efficiency remain significant challenges, especially for complex real-world applications. This paper addresses these challenges by proposing a novel neural adaptive empirical Bayes (NA-EB) framework. NA-EB leverages a class of implicit generative priors derived from low-dimensional distributions. This allows for efficient handling of complex data structures and …

abstract applications arxiv bayesian challenges computational cs.lg decision domains efficiency framework generative however making networks neural networks novel paper predictive prior quantification stat.ap type uncertainty world