Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.16506 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910802282283008 |
|---|---|
| author | Roberts, Gareth O. Rosenthal, Jeffrey S. |
| author_facet | Roberts, Gareth O. Rosenthal, Jeffrey S. |
| contents | We investigate the increase in efficiency of simulated and parallel tempering MCMC algorithms when using non-reversible updates to give them "momentum". By making a connection to a certain simple discrete Markov chain, we show that, under appropriate assumptions, the non-reversible algorithms still exhibit diffusive behaviour, just on a different time scale. We use this to argue that the optimally scaled versions of the non-reversible algorithms are indeed more efficient than the optimally scaled versions of their traditional reversible counterparts, but only by a modest speed-up factor of about 42%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_16506 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Quantifying the Speed-Up from Non-Reversibility in MCMC Tempering Algorithms Roberts, Gareth O. Rosenthal, Jeffrey S. Statistics Theory We investigate the increase in efficiency of simulated and parallel tempering MCMC algorithms when using non-reversible updates to give them "momentum". By making a connection to a certain simple discrete Markov chain, we show that, under appropriate assumptions, the non-reversible algorithms still exhibit diffusive behaviour, just on a different time scale. We use this to argue that the optimally scaled versions of the non-reversible algorithms are indeed more efficient than the optimally scaled versions of their traditional reversible counterparts, but only by a modest speed-up factor of about 42%. |
| title | Quantifying the Speed-Up from Non-Reversibility in MCMC Tempering Algorithms |
| topic | Statistics Theory |
| url | https://arxiv.org/abs/2501.16506 |