Generative Posterior Networks for Approximately Bayesian Epistemic Uncertainty Estimation

Autor:	Roderick, Melrose, Berkenkamp, Felix, Sheikholeslami, Fatemeh, Kolter, Zico
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	In many real-world problems, there is a limited set of training data, but an abundance of unlabeled data. We propose a new method, Generative Posterior Networks (GPNs), that uses unlabeled data to estimate epistemic uncertainty in high-dimensional problems. A GPN is a generative model that, given a prior distribution over functions, approximates the posterior distribution directly by regularizing the network towards samples from the prior. We prove theoretically that our method indeed approximates the Bayesian posterior and show empirically that it improves epistemic uncertainty estimation and scalability over competing methods. Comment: 10 pages, 3 figures, 2 tables
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2312.17411 Zobrazit plný text záznamu View this record from Arxiv