Quantifying the accuracy of approximate diffusions and Markov chains

by   Jonathan H. Huggins, et al.

Markov chains and diffusion processes are indispensable tools in machine learning and statistics that are used for inference, sampling, and modeling. With the growth of large-scale datasets, the computational cost associated with simulating these stochastic processes can be considerable, and many algorithms have been proposed to approximate the underlying Markov chain or diffusion. A fundamental question is how the computational savings trade off against the statistical error incurred due to approximations. This paper develops general results that address this question. We bound the Wasserstein distance between the equilibrium distributions of two diffusions as a function of their mixing rates and the deviation in their drifts. We show that this error bound is tight in simple Gaussian settings. Our general result on continuous diffusions can be discretized to provide insights into the computational-statistical trade-off of Markov chains. As an illustration, we apply our framework to derive finite-sample error bounds of approximate unadjusted Langevin dynamics. We characterize computation-constrained settings where, by using fast-to-compute approximate gradients in the Langevin dynamics, we obtain more accurate samples compared to using the exact gradients. Finally, as an additional application of our approach, we quantify the accuracy of approximate zig-zag sampling. Our theoretical analyses are supported by simulation experiments.


page 1

page 2

page 3

page 4


Simulating bridges using confluent diffusions

Diffusions are a fundamental class of models in many fields, including f...

Max Markov Chain

In this paper, we introduce Max Markov Chain (MMC), a novel representati...

Optimal Chernoff and Hoeffding Bounds for Finite Markov Chains

This paper develops an optimal Chernoff type bound for the probabilities...

Sampling, Diffusions, and Stochastic Localization

Diffusions are a successful technique to sample from high-dimensional di...

Randomised Wasserstein Barycenter Computation: Resampling with Statistical Guarantees

We propose a hybrid resampling method to approximate finitely supported ...

A New Truncation Algorithm for Markov Chain Equilibrium Distributions with Computable Error Bounds

This paper introduces a new algorithm for numerically computing equilibr...

The computational cost of blocking for sampling discretely observed diffusions

Many approaches for conducting Bayesian inference on discretely observed...

Please sign up or login with your details

Forgot password? Click here to reset