*******************************************************************
STATISTICS SEMINARS @ COLLEGIO CARLO ALBERTO
*******************************************************************
Venerdi 6 Maggio 2016 alle ore 16:00,
presso l’Aula Rossa del Collegio Carlo Alberto,
Moncalieri (TO), si terra' il seguente seminario:
Richard NICKL (University of Cambridge)
NONPARAMETRIC BAYESIAN INFERENCE FOR DISCRETELY SAMPLED DIFFUSIONS
We consider the nonlinear statistical inverse problem of
making inference on the unknown parameters of a diffusion process
describing the solution of a stochastic differential equation. The
observation regime is such that the process is sampled at discrete
time points that are a fixed distance apart, and we investigate the
asymptotic regime when more samples accrue in the time horizon (thus
avoiding unrealistic `high frequency’ assumptions). We shall briefly
review frequentist estimation techniques and then turn to Bayesian
nonparametric approaches to the problem, which have recently been
shown to be computationally tractable (work of A. Stuart, G. Roberts
and co-authors). A theory of frequentist contraction rates for the
posterior distribution has been elusive for several years, and we
present first rigorous, minimax optimal contraction rates for
posterior distributions arising from natural prior distributions on
infinite-dimensional parameter spaces on the drift and diffusion
coefficient. We will discuss what can be learnt from these results for
the choice of prior in such problems, as well as for the Bayesian
analysis of general nonlinear inverse problems. In the proofs we
obtain some new (functional) concentration inequalities for additive
functionals of Markov chains arising from diffusions that are of
independent interest.
This is joint work with Jakob Soehl (Cambridge),
see http://arxiv.org/abs/1510.05526
Tutti gli interessati sono invitati a partecipare.
Il seminario e' organizzato dalla "de Castro" Statistics Initiative
(http://www.carloalberto.org/stats) in collaborazione con il
Collegio Carlo Alberto.
Cordiali saluti,
Matteo Ruggiero
---
Matteo Ruggiero
University of Torino and Collegio Carlo Alberto
www.matteoruggiero.it
Seven PhD studentships will be available at University of Padova for
candidates
interested in the area of *Statistical Sciences* (*start of activities:
October 1st, 2016*).
*Eligibility*
The studentship competition is open to applicants of any age or citizenship,
holding a 2nd cycle degree or a single cycle degree from an Italian
university
or an equivalent qualification from other countries of at least four years'
duration (applicants can get their qualification no later than 30th
September 2016).
Admission is decided on the basis of qualifications only and does not
require
an entry examination.
*Award*
The award will be for three years, subject to satisfactory progress, at the
following rate: annual grant of euros 13.638,47 with a start date of 1
October 2016.
*How to apply*
The call will be published on *May 17 (deadline June 16)* at the page
http://www.unipd.it/ricerca/dottorati-di-ricerca/bandi-e-graduatorie
English version at the page
http://www.unipd.it/en/node/1053
*Applications are only accepted online*
*Further information*
See http://www.stat.unipd.it/fare-ricerca/ammissione
or contact phd(a)stat.unipd.it
Kindest regards,
Monica Chiogna
PhD Course Coordinator
CIME-EMS Summer School on Singular Random Dynamics
Cetraro (CS) - August 22 - August 27, 2016
Registration is open until end May at
http://web.math.unifi.it/users/cime/
MINI-COURSES
============
Massimiliano Gubinelli (IAM, Bonn)
Applications of controlled paths to problems in stochastic analysis
Martin Hairer (Univ. Warwick)
Stochastic PDEs and Renormalisation
Panagiotis Souganidis (Univ. Chicago)
Hamilton-Jacobi partial differential equations and conservation laws
with rough time signals and applications
Nikolay Tzvetkov (Univ. Cergy-Pontoise)
On Hamiltonian partial differential equations with random initial
conditions
============
We look forward to seeing you in Cetraro,
Franco Flandoli, Massimiliano Gubinelli, Martin Hairer
Lunedì 9 Maggio 2016 alle ore 14:00,
presso l’Aula 1B1 dip. SBAI
Università La Sapienza di Roma,
si terra' il seguente seminario:
SPEAKER: Bill Hsin-Hsiung Huang, Ph.D. (Dep. Of Statistics University of
Central Florida)
TITLE: An Affine-Invariant Bayesian Cluster Process with Split-Merge Gibbs
Sampler
ABSTRACT:
We develop a clustering algorithm which does not requires knowing the
number of clusters in advance. Furthermore, our clustering method is
rotation-, scale- and translation-invariant coordinatewise. We call it
“Affine-invariant Bayesian (AIB) process”. A highly efficient split-merge
Gibbs sampling algorithm is proposed. Using the Ewens sampling distribution
as prior of the partition and the profile residual likelihoods of the
responses under three different covariance matrix structures, we obtain
inferences in the form of a posterior distribution on partitions. The
proposed split-merge MCMC algorithm successfully and efficiently estimate
the partition. Our experimental results indicate that the AIB process
outperforms other competing methods. In addition, the proposed algorithm is
irreducible and aperiodic, so that the estimate is guaranteed to converge
to the posterior distribution.
Tutti gli interessati sono invitati a partecipare.
Cordiali saluti,
Daniela De Canditiis
--
Daniela De Canditiis, PhD
Istituto per le Applicazioni del Calcolo "M.Picone" (CNR)
via dei Taurini, 19 -- 00185 Roma, Italy
tel: +39 06 49270942
fax: +39 06 4404306
http://www.iac.rm.cnr.it/~danielad/