In this work, minibatch MCMC sampling for feedforward neural networks is made more feasible. To this end, it is proposed to sample subgroups of parameters via a blocked Gibbs sampling scheme. By partitioning the parameter space, sampling is possible irrespective of layer width. It is also possible to alleviate vanishing acceptance rates for increasing depth by reducing the proposal variance in deeper layers. Increasing the length of a non-convergent chain increases the predictive accuracy in classification tasks, so avoiding vanishing acceptance rates and consequently enabling longer chain runs have practical benefits. Moreover, non-convergent chain realizations aid in the quantification of predictive uncertainty. An open problem is how to perform minibatch MCMC sampling for feedforward neural networks in the presence of augmented data.
翻译:在这项工作中,为饲料向神经网络采集的小型组合MCMC取样变得更为可行。为此,建议通过封闭的Gibbs取样办法对参数分组进行抽样。通过分割参数空间,取样是可能的,而不论分层宽度如何。通过减少更深层次的建议差异,也可以减少深度的消失接受率。增加非趋同链的长度可以提高分类任务的预测准确性,从而避免消失接受率,从而促成较长链条的运行。此外,非趋同链的实现有助于预测不确定性的量化。一个公开的问题是,如何在扩大的数据面前进行微型组合的MCMC取样,供饲料向神经网络使用。