Geometry-informed irreversible perturbations for accelerated convergence of Langevin dynamics

08/18/2021
by   Benjamin J. Zhang, et al.
0

We introduce a novel geometry-informed irreversible perturbation that accelerates convergence of the Langevin algorithm for Bayesian computation. It is well documented that there exist perturbations to the Langevin dynamics that preserve its invariant measure while accelerating its convergence. Irreversible perturbations and reversible perturbations (such as Riemannian manifold Langevin dynamics (RMLD)) have separately been shown to improve the performance of Langevin samplers. We consider these two perturbations simultaneously by presenting a novel form of irreversible perturbation for RMLD that is informed by the underlying geometry. Through numerical examples, we show that this new irreversible perturbation can improve performance of the estimator over reversible perturbations that do not take the geometry into account. Moreover we demonstrate that irreversible perturbations generally can be implemented in conjunction with the stochastic gradient version of the Langevin algorithm. Lastly, while continuous-time irreversible perturbations cannot impair the performance of a Langevin estimator, the situation can sometimes be more complicated when discretization is considered. To this end, we describe a discrete-time example in which irreversibility increases both the bias and variance of the resulting estimator.

READ FULL TEXT

page 16

page 17

research
02/07/2023

Learning Discretized Neural Networks under Ricci Flow

In this paper, we consider Discretized Neural Networks (DNNs) consisting...
research
09/26/2020

Adaptive Non-reversible Stochastic Gradient Langevin Dynamics

It is well known that adding any skew symmetric matrix to the gradient o...
research
07/05/2019

Restart perturbations for lazy, reversible Markov chains: trichotomy and pre-cutoff equivalence

Given a lazy, reversible Markov chain with n states and transition matri...
research
09/18/2022

EMaP: Explainable AI with Manifold-based Perturbations

In the last few years, many explanation methods based on the perturbatio...
research
12/20/2022

Generalized Simultaneous Perturbation Stochastic Approximation with Reduced Estimator Bias

We present in this paper a family of generalized simultaneous perturbati...
research
06/15/2022

Deterministic and Random Perturbations of the Kepler Problem

We investigate perturbations in the Kepler problem. We offer an overview...
research
07/24/2021

Theoretical Study and Comparison of SPSA and RDSA Algorithms

Stochastic approximation (SA) algorithms are widely used in system optim...

Please sign up or login with your details

Forgot password? Click here to reset