A scalable bayesian sampling method based on stochastic gradient descent isotropization

Giulio Franzese*, Dimitrios Milios, Maurizio Filippone, Pietro Michiardi

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Scopus citations


Stochastic gradient SG-based algorithms for Markov chain Monte Carlo sampling (SGMCMC) tackle large-scale Bayesian modeling problems by operating on mini-batches and injecting noise on SGsteps. The sampling properties of these algorithms are determined by user choices, such as the covariance of the injected noise and the learning rate, and by problem-specific factors, such as assumptions on the loss landscape and the covariance of SG noise. However, current SGMCMC algorithms applied to popular complex models such as Deep Nets cannot simultaneously satisfy the assumptions on loss landscapes and on the behavior of the covariance of the SG noise, while operating with the practical requirement of non-vanishing learning rates. In this work we propose a novel practical method, which makes the SG noise isotropic, using a fixed learning rate that we determine analytically. Extensive experimental validations indicate that our proposal is competitive with the state of the art on SGMCMC.

Original languageEnglish (US)
Article number1426
Issue number11
StatePublished - Nov 2021

Bibliographical note

Publisher Copyright:
© 2021 by the authors. Licensee MDPI, Basel, Switzerland.


  • Bayesian sampling
  • Monte Carlo integration
  • Stochastic gradients

ASJC Scopus subject areas

  • Information Systems
  • Mathematical Physics
  • Physics and Astronomy (miscellaneous)
  • Electrical and Electronic Engineering


Dive into the research topics of 'A scalable bayesian sampling method based on stochastic gradient descent isotropization'. Together they form a unique fingerprint.

Cite this