论文标题
有吸引力的抑制性MCMC算法的收敛速率
Convergence Rates of Attractive-Repulsive MCMC Algorithms
论文作者
论文摘要
我们考虑了某些粒子系统的MCMC算法，包括吸引力和排斥力，使它们的收敛分析具有挑战性。我们证明，在有界状态空间上的这些算法的一个版本均匀地具有偏古性，并且具有明确的定量收敛速率。我们还证明，无界状态空间上的一个版本仍然是几何偏度的，然后使用移位耦合的方法来获得其收敛速率的显式定量界限。
We consider MCMC algorithms for certain particle systems which include both attractive and repulsive forces, making their convergence analysis challenging. We prove that a version of these algorithms on a bounded state space is uniformly ergodic with an explicit quantitative convergence rate. We also prove that a version on an unbounded state-space is still geometrically ergodic, and then use the method of shift-coupling to obtain an explicit quantitative bound on its convergence rate.
