Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling. (arXiv:2205.08766v1 [cs.LG])

Principled Bayesian deep learning (BDL) does not live up to its potential
when we only focus on marginal predictive distributions (marginal predictives).
Recent works have highlighted the importance of joint predictives for
(Bayesian) sequential decision making from a theoretical and synthetic
perspective. We provide additional practical arguments grounded in real-world
applications for focusing on joint predictives: we discuss online Bayesian
inference, which would allow us to make predictions while taking into account
additional data without retraining, and we propose new …

active learning arxiv bayesian bayesian inference inference learning sampling