Biases in variational Bayesian neural networks
Thang Bui
Abstract
Variational inference recently became the de facto standard method for approximate Bayesian neural networks. However, the standard mean-field approach (MFVI) possesses many undesirable behaviours. This short paper empirically investigates the variational biases of MFVI and other variational families. The preliminary results shed light on the poor performance of many variational approaches for model selection.
Chat is not available.
Successful Page Load