Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

A Variational View on Bootstrap Ensembles as Bayesian Inference

Abstract : In this paper, we employ variational arguments to establish a connection between ensemble methods for Neural Networks and Bayesian inference. We consider an ensemble-based scheme where each model/particle corresponds to a perturbation of the data by means of parametric bootstrap and a perturbation of the prior. We derive conditions under which any optimization steps of the particles makes the associated distribution reduce its divergence to the posterior over model parameters. Such conditions do not require any particular form for the approximation and they are purely geometrical, giving insights on the behavior of the ensemble on a number of interesting models such as Neural Networks with ReLU activations. Experiments confirm that ensemble methods can be a valid alternative to approximate Bayesian inference; the theoretical developments in the paper seek to explain this behavior.
Document type :
Preprints, Working Papers, ...
Complete list of metadata
Contributor : Centre de Documentation Eurecom Connect in order to contact the contributor
Submitted on : Wednesday, September 15, 2021 - 11:58:37 AM
Last modification on : Thursday, September 16, 2021 - 3:40:44 AM

Links full text


  • HAL Id : hal-03344974, version 1
  • ARXIV : 2006.04548



Dimitrios Milios, Pietro Michiardi, Maurizio Filippone. A Variational View on Bootstrap Ensembles as Bayesian Inference. 2020. ⟨hal-03344974⟩



Les métriques sont temporairement indisponibles