Good initializations of variational bayes for deep models

Simone Rossi*, Pietro Michiardi, Maurizio Filippone

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

Stochastic variational inference is an established way to carry out approximate Bayesian inference for deep models flexibly and at scale. 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 Deep Nets and Conv Nets, showing faster and better convergence compared to alternatives inspired by the literature on initializations for loss minimization.

Original languageEnglish (US)
Title of host publication36th International Conference on Machine Learning, ICML 2019
PublisherInternational Machine Learning Society (IMLS)
Pages9659-9669
Number of pages11
ISBN (Electronic)9781510886988
StatePublished - 2019
Event36th International Conference on Machine Learning, ICML 2019 - Long Beach, United States
Duration: Jun 9 2019Jun 15 2019

Publication series

Name36th International Conference on Machine Learning, ICML 2019
Volume2019-June

Conference

Conference36th International Conference on Machine Learning, ICML 2019
Country/TerritoryUnited States
CityLong Beach
Period06/9/1906/15/19

ASJC Scopus subject areas

  • Education
  • Computer Science Applications
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'Good initializations of variational bayes for deep models'. Together they form a unique fingerprint.

Cite this