Convergence rate bounds for iterative random functions using one-shot coupling
Authors:
- Sabrina SixtaSSSabrina Sixta
- Jeffrey S. RosenthalJRJeffrey S. Rosenthal
Preprint
Abstract
One-shot coupling is a method of bounding the convergence rate between two copies of a Markov chain in total variation distance, which was first introduced by Roberts and Rosenthal and generalized by Madras and Sezer. The method is divided into two parts: the contraction phase, when the chains converge in expected distance and the coalescing phase, which occurs at the last iteration, when there is an attempt to couple. One-shot coupling does not require the use of any exogenous variables like a drift function or a minorization constant. In this paper, we summarize the one-shot coupling method into the One-Shot Coupling Theorem. We then apply the theorem to two families of Markov chains: the random functional autoregressive process and the autoregressive conditional heteroscedastic (ARCH) process. We provide multiple examples of how the theorem can be used on various models including ones in high dimensions. These examples illustrate how the theorem's conditions can be verified in a straightforward way. The one-shot coupling method appears to generate tight geometric convergence rate bounds.Keywords
All Related Versions
This publication has 39 references indexed in Scilit:
- Linear Algebra and Optimization for Machine Learning2020
- Stochastic Models for Time Series2018
- Introduction to Time Series and Forecasting2016
- A First Course in Bayesian Statistical Methods2009
- Analysis by Its History2008
- Faithful Couplings of Markov Chains: Now Equals ForeverAdvances in Applied Mathematics, 1997
- Lectures on finite Markov chains1997
- Analysis of the Gibbs sampler for a model related to James-Stein estimatorsStatistics and Computing, 1996
- Markov Chains and Stochastic Stability1993
- A splitting technique for Harris recurrent Markov chainsProbability Theory and Related Fields, 1978