Grstats Forum
AUEB Stats Seminars 5/2/2021: Manifold Markov chain Monte Carlo methods for Bayesian inference in a wide class of diffusion models Forumgrstats
Grstats Forum
Θέλετε να αντιδράσετε στο μήνυμα; Φτιάξτε έναν λογαριασμό και συνδεθείτε για να συνεχίσετε.

AUEB Stats Seminars 5/2/2021: Manifold Markov chain Monte Carlo methods for Bayesian inference in a wide class of diffusion models

Πήγαινε κάτω

AUEB Stats Seminars 5/2/2021: Manifold Markov chain Monte Carlo methods for Bayesian inference in a wide class of diffusion models Empty AUEB Stats Seminars 5/2/2021: Manifold Markov chain Monte Carlo methods for Bayesian inference in a wide class of diffusion models

Δημοσίευση από grstats Την / Το Τετ 11 Νοε 2020 - 14:57

ΚΥΚΛΟΣ ΣΕΜΙΝΑΡΙΩΝ ΣΤΑΤΙΣΤΙΚΗΣ ΦΕΒΡΟΥΑΡΙΟΣ 2021

AUEB Stats Seminars 5/2/2021: Manifold Markov chain Monte Carlo methods for Bayesian inference in a wide class of diffusion models Beskos10

Alexandros Beskos
Associate Professor in Statistics, Department of Statistical Science, UCL, UK

Manifold Markov chain Monte Carlo methods for Bayesian inference in a wide class of diffusion models

ΠΑΡΑΣΚΕΥΗ 5/2/2021
13:30

Σύνδεσμος Google Meeting: meet.google.com/nub-bxuf-zsn

ΠΕΡΙΛΗΨΗ

Bayesian inference for nonlinear diffusions, observed at discrete times, is a challenging task that has prompted the development of a number of algorithms, mainly within the Computational Statistics community. We propose a new direction, and accompanying methodology, for inferring the posterior distribution of latent diffusion paths and model parameters, given partial observations of the process -- borrowing ideas from constrained Hamiltonian dynamics studied in mechanics and molecular dynamics. Joint configurations of the underlying process noise and of parameters, mapping onto diffusion paths consistent with observations, form an implicitly defined manifold. Then, by making use of a constrained Hamiltonian Monte Carlo algorithm on the embedded manifold, we are able to perform computationally efficient inference for an extensive class of discretely observed diffusion models. Critically, in contrast with other approaches proposed in the literature, our methodology is highly automated, requiring minimal user intervention and applying alike in a range of settings, including: elliptic or hypo-elliptic systems; observations with or without noise; linear or non-linear observation operators. Exploiting Markovianity, we propose a variant of the method with complexity that scales linearly in the resolution of path discretisation and the number of observation times. Example Python code is given at git.io/m-mcmc.


Fb event: https://www.facebook.com/events/1605802756271910/
grstats
grstats

Posts : 837
Join date : 21/10/2009

http://stat-athens.aueb.gr/~grstats/

Επιστροφή στην κορυφή Πήγαινε κάτω

Επιστροφή στην κορυφή


 
Δικαιώματα σας στην κατηγορία αυτή
Δεν μπορείτε να απαντήσετε στα Θέματα αυτής της Δ.Συζήτησης