Metropolis Monte Carlo sampling: convergence, localization transition and optimality
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2022
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929198571978752 |
|---|---|
| author | Chepelianskii, Alexei D. Majumdar, Satya N. Schawe, Hendrik Trizac, Emmanuel |
| author_facet | Chepelianskii, Alexei D. Majumdar, Satya N. Schawe, Hendrik Trizac, Emmanuel |
| contents | Among random sampling methods, Markov Chain Monte Carlo algorithms are foremost. Using a combination of analytical and numerical approaches, we study their convergence properties towards the steady state, within a random walk Metropolis scheme. Analysing the relaxation properties of some model algorithms sufficiently simple to enable analytic progress, we show that the deviations from the target steady-state distribution can feature a localization transition as a function of the characteristic length of the attempted jumps defining the random walk. While the iteration of the Monte Carlo algorithm converges to equilibrium for all choices of jump parameters, the localization transition changes drastically the asymptotic shape of the difference between the probability distribution reached after a finite number of steps of the algorithm and the target equilibrium distribution. We argue that the relaxation before and after the localisation transition is respectively limited by diffusion and rejection rates. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2207_10488 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Metropolis Monte Carlo sampling: convergence, localization transition and optimality Chepelianskii, Alexei D. Majumdar, Satya N. Schawe, Hendrik Trizac, Emmanuel Statistical Mechanics Machine Learning Computation Among random sampling methods, Markov Chain Monte Carlo algorithms are foremost. Using a combination of analytical and numerical approaches, we study their convergence properties towards the steady state, within a random walk Metropolis scheme. Analysing the relaxation properties of some model algorithms sufficiently simple to enable analytic progress, we show that the deviations from the target steady-state distribution can feature a localization transition as a function of the characteristic length of the attempted jumps defining the random walk. While the iteration of the Monte Carlo algorithm converges to equilibrium for all choices of jump parameters, the localization transition changes drastically the asymptotic shape of the difference between the probability distribution reached after a finite number of steps of the algorithm and the target equilibrium distribution. We argue that the relaxation before and after the localisation transition is respectively limited by diffusion and rejection rates. |
| title | Metropolis Monte Carlo sampling: convergence, localization transition and optimality |
| topic | Statistical Mechanics Machine Learning Computation |
| url | https://arxiv.org/abs/2207.10488 |