Abstract
We describe parallel Markov chain Monte Carlo methods that propagate a collective ensemble of paths, with local covariance information calculated from neighbouring replicas. The use of collective dynamics eliminates multiplicative noise and stabilizes the dynamics, thus providing a practical approach to difficult anisotropic sampling problems in high dimensions. Numerical experiments with model problems demonstrate that dramatic potential speedups, compared to various alternative schemes, are attainable.
Original language | English (US) |
---|---|
Pages (from-to) | 277-290 |
Number of pages | 14 |
Journal | Statistics and Computing |
Volume | 28 |
Issue number | 2 |
DOIs | |
State | Published - Mar 1 2018 |
Keywords
- BFGS
- Brownian dynamics
- Computational statistics
- Langevin methods
- MCMC
- Machine learning
- Markov chain Monte Carlo
- Stochastic sampling
ASJC Scopus subject areas
- Theoretical Computer Science
- Statistics and Probability
- Statistics, Probability and Uncertainty
- Computational Theory and Mathematics