Français
The coordinate sampler: a non-reversible Gibbs-like MCMC sampler
Virtualconference
Authors : Robert, Christian P (Author of the conference)
CIRM (Publisher )
60J25 - Continuous-time Markov processes on general state spaces
62F15 - Bayesian inference
CIRM (Publisher )
Loading the player...
|
Abstract :
In this talk, we derive a novel non-reversible, continuous-time Markov chain Monte Carlo (MCMC) sampler, called Coordinate Sampler, based on a piecewise deterministic Markov process (PDMP), which can be seen as a variant of the Zigzag sampler. In addition to proving a theoretical validation for this new sampling algorithm, we show that the Markov chain it induces exhibits geometrical ergodicity convergence, for distributions whose tails decay at least as fast as an exponential distribution and at most as fast as a Gaussian distribution. Several numerical examples highlight that our coordinate sampler is more efficient than the Zigzag sampler, in terms of effective sample size.
[This is joint work with Wu Changye, ref. arXiv:1809.03388]
Keywords : MCMC; no-reversibility; Gibbs sampling
MSC Codes : [This is joint work with Wu Changye, ref. arXiv:1809.03388]
Keywords : MCMC; no-reversibility; Gibbs sampling
60J25 - Continuous-time Markov processes on general state spaces
62F15 - Bayesian inference
|
Information on the Video
Film maker : Hennenfent, GuillaumeLanguage : English Available date : 02/11/2020 Conference Date : 02/11/2020 Subseries : Research School arXiv category : Statistics Theory Mathematical Area(s) : Probability & Statistics Format : MP4 (.mp4) - HD Video Time : 00:32:44 Targeted Audience : Researchers Download : https://videos.cirm-math.fr/2020-11-05_Robert.mp4 
|
Information on the Event
Event Title : Jean-Morlet Chair 2020 - Research School: Quasi-Monte Carlo Methods and Applications / Chaire Jean-Morlet 2020 - Ecole: Méthode de quasi-Monte-Carlo et applicationsEvent Organizers : Rivat, Joël ; Thonhauser, Stefan ; Tichy, Robert Dates : 02/11/2020 - 07/11/2020 Event Year : 2020 Event URL : https://www.chairejeanmorlet.com/2255.html
Citation Data
DOI : 10.24350/CIRM.V.19664703Cite this video as: Robert, Christian P (2020). The coordinate sampler: a non-reversible Gibbs-like MCMC sampler. CIRM. Audiovisual resource. doi:10.24350/CIRM.V.19664703 URI : http://dx.doi.org/10.24350/CIRM.V.19664703 |
See Also
- [Virtualconference] PDMPs in risk theory and QMC integration III / Author of the conference Thonhauser, Stefan.
- [Virtualconference] On the estimation of conditional quantiles - lecture 3 / Author of the conference Maume-Deschamps, Véronique.
- [Virtualconference] On the estimation of conditional quantiles - lecture 2 / Author of the conference Maume-Deschamps, Véronique.
- [Virtualconference] Stochastic differential equations / Author of the conference Leobacher, Gunther.
- [Virtualconference] Number sequences for simulation - lecture 2 / Author of the conference Ökten, Giray.
- [Virtualconference] PDMPs and Integrals PDMPs in risk theory and QMC integration II / Author of the conference Thonhauser, Stefan.
- [Virtualconference] Derivative pricing, simulation from non-uniform distributions - lecture 3 / Author of the conference Ökten, Giray.
- [Multi angle] Quasi-Monte Carlo methods and applications: introduction / Author of the conference Tichy, Robert.
- [Virtualconference] Risk theory: models and objectives PDMPs in risk theory and QMC integration I / Author of the conference Thonhauser, Stefan.
- [Virtualconference] On the estimation of conditional quantiles - lecture 1 / Author of the conference Maume-Deschamps, Véronique.
- [Virtualconference] Brief introduction of Quasi-Monte Carlo Methods and their Applications / Author of the conference Leobacher, Gunther.
- [Virtualconference] Two concrete FinTech applications of QMC / Author of the conference Larcher, Gerhard.
- [Virtualconference] Number sequences for simulation - lecture 1 / Author of the conference Ökten, Giray.
- [Virtualconference] Optimizing dividends and limited capital injections via exponential approximations I / Author of the conference Avram, Florin.
Bibliography
- WU, Changye et ROBERT, Christian P. Coordinate sampler: a non-reversible Gibbs-like MCMC sampler. Statistics and Computing, 2020, vol. 30, no 3, p. 721-730. - https://doi.org/10.1007/s11222-019-09913-w
