Variance reduction for Langevin Monte Carlo in high dimensional sampling problems

06/10/2020
by   Zhiyan Ding, et al.
5

Sampling from a log-concave distribution function is one core problem that has wide applications in Bayesian statistics and machine learning. While most gradient free methods have slow convergence rate, the Langevin Monte Carlo (LMC) that provides fast convergence requires the computation of gradients. In practice one uses finite-differencing approximations as surrogates, and the method is expensive in high-dimensions. A natural strategy to reduce computational cost in each iteration is to utilize random gradient approximations, such as random coordinate descent (RCD) or simultaneous perturbation stochastic approximation (SPSA).We show by a counterexample that blindly applying RCD does not achieve the goal in the most general setting. The high variance induced by the randomness means a larger number of iterations are needed, and this balances out the saving in each iteration. We then introduce a new variance reduction approach, termed Randomized Coordinates Averaging Descent (RCAD), and incorporate it with both overdamped and underdamped LMC. The methods are termed RCAD-O-LMC and RCAD-U-LMC respectively. The methods still sit in the random gradient approximation framework, and thus the computational cost in each iteration is low. However, by employing RCAD, the variance is reduced, so the methods converge within the same number of iterations as the classical overdamped and underdamped LMC. This leads to a computational saving overall.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/26/2020

Langevin Monte Carlo: random coordinate descent and variance reduction

Sampling from a log-concave distribution function on ℝ^d (with d≫ 1) is ...
research
02/08/2021

Constrained Ensemble Langevin Monte Carlo

The classical Langevin Monte Carlo method looks for i.i.d. samples from ...
research
01/27/2020

Variance Reduction with Sparse Gradients

Variance reduction methods such as SVRG and SpiderBoost use a mixture of...
research
08/04/2023

Generative Modelling of Lévy Area for High Order SDE Simulation

It is well known that, when numerically simulating solutions to SDEs, ac...
research
10/22/2020

Random Coordinate Underdamped Langevin Monte Carlo

The Underdamped Langevin Monte Carlo (ULMC) is a popular Markov chain Mo...
research
10/03/2020

Random Coordinate Langevin Monte Carlo

Langevin Monte Carlo (LMC) is a popular Markov chain Monte Carlo samplin...
research
05/24/2019

Computational cost for determining an approximate global minimum using the selection and crossover algorithm

This work examines the expected computational cost to determine an appro...

Please sign up or login with your details

Forgot password? Click here to reset