Stochastic Gradient Hamiltonian Monte Carlo with Variance Reduction for Bayesian Inference

03/29/2018
by   Zhize Li, et al.
0

Gradient-based Monte Carlo sampling algorithms, like Langevin dynamics and Hamiltonian Monte Carlo, are important methods for Bayesian inference. In large-scale settings, full-gradients are not affordable and thus stochastic gradients evaluated on mini-batches are used as a replacement. In order to reduce the high variance of noisy stochastic gradients, [Dubey et al., 2016] applied the standard variance reduction technique on stochastic gradient Langevin dynamics and obtained both theoretical and experimental improvements. In this paper, we apply the variance reduction tricks on Hamiltonian Monte Carlo and achieve better theoretical convergence results compared with the variance-reduced Langevin dynamics. Moreover, we apply the symmetric splitting scheme in our variance-reduced Hamiltonian Monte Carlo algorithms to further improve the theoretical results. The experimental results are also consistent with the theoretical results. As our experiment shows, variance-reduced Hamiltonian Monte Carlo demonstrates better performance than variance-reduced Langevin dynamics in Bayesian regression and classification tasks on real-world datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/02/2021

Exact Langevin Dynamics with Stochastic Gradients

Stochastic gradient Markov Chain Monte Carlo algorithms are popular samp...
research
06/08/2015

Gradient-free Hamiltonian Monte Carlo with Efficient Kernel Exponential Families

We propose Kernel Hamiltonian Monte Carlo (KMC), a gradient-free adaptiv...
research
06/30/2021

Revisiting the Effects of Stochasticity for Hamiltonian Samplers

We revisit the theoretical properties of Hamiltonian stochastic differen...
research
06/20/2022

Mobility estimation for Langevin dynamics using control variates

The scaling of the mobility of two-dimensional Langevin dynamics in a pe...
research
10/14/2020

Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splitting

Hamiltonian Monte Carlo (HMC) is a Markov chain Monte Carlo (MCMC) appro...
research
02/09/2021

A New Framework for Variance-Reduced Hamiltonian Monte Carlo

We propose a new framework of variance-reduced Hamiltonian Monte Carlo (...
research
05/12/2018

Predictive Uncertainty in Large Scale Classification using Dropout - Stochastic Gradient Hamiltonian Monte Carlo

Predictive uncertainty is crucial for many computer vision tasks, from i...

Please sign up or login with your details

Forgot password? Click here to reset