TL;DR本文为解决Bayesian深度学习中的先验分布选择困难性问题,提出了一种基于Gaussian processes的新颖的功能先验分布匹配框架,该框架可通过 Markov chain Monte Carlo方法进行可扩展的先验分布采样,从而显著提高了性能。
Abstract
The Bayesian treatment of neural networks dictates that a prior distribution is specified over their weight and bias parameters. This poses a challenge because modern neural networks are characterized by a large