Revisiting the Effects of Stochasticity for Hamiltonian Samplers - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year : 2021

Revisiting the Effects of Stochasticity for Hamiltonian Samplers

Maurizio Filippone
  • Function : Author
  • PersonId : 1021042
Pietro Michiardi
  • Function : Author
  • PersonId : 1084771

Abstract

We revisit the theoretical properties of Hamiltonian stochastic differential equations (SDES) for Bayesian posterior sampling, and we study the two types of errors that arise from numerical SDE simulation: the discretization error and the error due to noisy gradient estimates in the context of data subsampling. Our main result is a novel analysis for the effect of mini-batches through the lens of differential operator splitting, revising previous literature results. The stochastic component of a Hamiltonian SDE is decoupled from the gradient noise, for which we make no normality assumptions. This leads to the identification of a convergence bottleneck: when considering mini-batches, the best achievable error rate is

Dates and versions

hal-03344742 , version 1 (15-09-2021)

Identifiers

Cite

Giulio Franzese, Dimitrios Milios, Maurizio Filippone, Pietro Michiardi. Revisiting the Effects of Stochasticity for Hamiltonian Samplers. 2021. ⟨hal-03344742⟩
57 View
0 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More