Complexity Bounds for MCMC via Diffusion Limits

Abstract

We connect known results about diffusion limits of Markov chain Monte Carlo (MCMC) algorithms to the Computer Science notion of algorithm complexity. Our main result states that any diffusion limit of a Markov process implies a corresponding complexity bound (in an appropriate metric). We then combine this result with previously-known MCMC diffusion limit results to prove that under appropriate assumptions, the Random-Walk Metropolis (RWM) algorithm in $d$ dimensions takes $O(d)$ iterations to converge to stationarity, while the Metropolis-Adjusted Langevin Algorithm (MALA) takes $O(d^{1/3})$ iterations to converge to stationarity.

References in corpus (6)

• MCMC using Hamiltonian dynamics
• General state space Markov chains and MCMC algorithms
• Conditions for rapid mixing of parallel and simulated tempering on multimodal distributions
• Optimal scaling for partially updating MCMC algorithms
• Optimal scaling of the random walk Metropolis on elliptically symmetric unimodal targets
• Optimal scaling for the transient phase of Metropolis Hastings algorithms: The longtime behavior

Cited by in corpus (2)

• Log-concave sampling: Metropolis-Hastings algorithms are fast
• An introduction to computational complexity in Markov Chain Monte Carlo methods