English

Good Initializations of Variational Bayes for Deep Models

Machine Learning 2019-01-28 v2 Machine Learning

Abstract

Stochastic variational inference is an established way to carry out approximate Bayesian inference for deep models. While there have been effective proposals for good initializations for loss minimization in deep learning, far less attention has been devoted to the issue of initialization of stochastic variational inference. We address this by proposing a novel layer-wise initialization strategy based on Bayesian linear models. The proposed method is extensively validated on regression and classification tasks, including Bayesian DeepNets and ConvNets, showing faster and better convergence compared to alternatives inspired by the literature on initializations for loss minimization.

Keywords

Cite

@article{arxiv.1810.08083,
  title  = {Good Initializations of Variational Bayes for Deep Models},
  author = {Simone Rossi and Pietro Michiardi and Maurizio Filippone},
  journal= {arXiv preprint arXiv:1810.08083},
  year   = {2019}
}

Comments

8 pages of main paper (+3 for references and +6 of supplement material)

R2 v1 2026-06-23T04:44:38.617Z