arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.12907stat.MLcs.LGmath.PRmath.STstat.TH
收藏

具有不对称动量分布的哈密顿蒙特卡洛方法

Hamiltonian Monte Carlo with Asymmetrical Momentum Distributions

IBM T.J. Watson Research Center(IBM T.J.沃森研究所以)

Soumyadip Ghosh, Yingdong Lu, Tomasz Nowicki

AI总结:

本文提出改进的AD-HMC方法,通过打破自共轭性要求实现更弱条件下的几何收敛,适用于一般辅助分布。

摘要:

本文提出改进的AD-HMC方法,通过打破自共轭性要求实现更弱条件下的几何收敛,适用于一般辅助分布。

英文摘要:

Existing rigorous convergence guarantees for the Hamiltonian Monte Carlo (HMC) algorithm use Gaussian auxiliary momentum variables, which are crucially symmetrically distributed. We present a novel convergence analysis for HMC utilizing new dynamical and probabilistic arguments. The convergence is rigorously established under significantly weaker conditions, which among others allow for general auxiliary distributions. In our framework, we show that plain HMC with asymmetrical momentum distributions breaks a key self-adjointness requirement. We propose a modified version of HMC, that we call the Alternating Direction HMC (AD-HMC), which overcomes this difficulty. Sufficient conditions are established under which AD-HMC exhibits geometric convergence in Wasserstein distance. The geometric convergence analysis is extended to when the Hamiltonian motion is approximated by the leapfrog symplectic integrator, where an additional Metropolis-Hastings rejection step is required. Numerical experiments suggest that AD-HMC can generalize a popular dynamic auxiliary scheme to show improved performance over HMC with Gaussian auxiliaries.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑