Parallel-tempered Stochastic Gradient Hamiltonian Monte Carlo for Approximate Multimodal Posterior Sampling

12/04/2018
by   Rui Luo, et al.
0

We propose a new sampler that integrates the protocol of parallel tempering with the Nosé-Hoover (NH) dynamics. The proposed method can efficiently draw representative samples from complex posterior distributions with multiple isolated modes in the presence of noise arising from stochastic gradient. It potentially facilitates deep Bayesian learning on large datasets where complex multimodal posteriors and mini-batch gradient are encountered.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/29/2019

Replica-exchange Nosé-Hoover dynamics for Bayesian learning on large datasets

In this paper, we propose a new sampler for Bayesian learning that can e...
research
06/05/2017

Stochastic Gradient Monomial Gamma Sampler

Recent advances in stochastic gradient techniques have made it possible ...
research
11/30/2017

Thermostat-assisted Continuous-tempered Hamiltonian Monte Carlo for Multimodal Posterior Sampling

In this paper, we propose a new sampling method named as the thermostat-...
research
02/20/2022

Interacting Contour Stochastic Gradient Langevin Dynamics

We propose an interacting contour stochastic gradient Langevin dynamics ...
research
10/11/2018

Stochastic Approximation Hamiltonian Monte Carlo

Recently, the Hamilton Monte Carlo (HMC) has become widespread as one of...
research
09/14/2019

A Bayesian Approach for De-duplication in the Presence of Relational Data

In this paper we study the impact of combining profile and network data ...
research
05/07/2023

Bayesian Over-the-Air FedAvg via Channel Driven Stochastic Gradient Langevin Dynamics

The recent development of scalable Bayesian inference methods has renewe...

Please sign up or login with your details

Forgot password? Click here to reset