Marcelo Pereyra | Welcome

Maxwell Insitute for Mathematical Sciences
School of Mathematical and Computer Sciences, Heriot-Watt University

News

Conference I be chairing the next IMA conference on Inverse Problems, which will take place in Edinburgh at the ICMS in May 2021. More details soon!

EPSRC Project BOLT I am starting a new three-year project, funded by EPSRC, to develop new Bayesian methodology for blind and semi-blind bilinear inverse problems in imaging sciences, in collaboration with colleagues at Ecole Normale Superieure Cachan and at UCL Mullard Space Science Laboratory. The aim is to develop new computational and analysis methods for objectively comparing, selecting, and calibrating computational imaging models directly from the observed data in a fully unsupervised way. I am currently hiring a PDRA to start in Sep. 2020. A fully-funded PhD position, with no nationality restrictions, will be advertised shortly. More details soon!

New paper I am glad to report that the paper "Accelerating proximal Markov chain Monte Carlo by using explicit stabilised methods" with Luis Vargas and Kostas Zygalakis has been accepted for publication in SIAM J. Imaging Sciences. Pre-print avialable at https://arxiv.org/abs/1908.08845

Promotion I have been promoted to Associate Professor in Statistics :-)

New companion papers Following two years of intense work, Ana F. Vidal, Valentin De Bortoli, Alain Durmus and I have proudly realeased these two long companion papers on new computation methodology for empirical Bayesian estimation in high-dimentional inverse problems:
1) A. F. Vidal, V. De Bortoli, M. Pereyra, A. Durmus, "Maximum likelihood estimation of regularisation parameters in high-dimensional inverse problems: an empirical Bayesian approach", available at https://arxiv.org/abs/1911.11709.
2) V. De Bortoli, A. F. Vidal, A. Durmus, M. Pereyra, "Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation", available at https://arxiv.org/abs/1906.12281.

Talk at the Institut Henri Poincaré You can find my talk on "Bayesian inference and convex geometry: theory, methods, and algorithms" here.

Winter School The slides for my 6-hour course on "Bayesian inference and mathematical imaging" at the CIRM school on "The Mathematics of Imaging" are available here:
Part I: Bayesian analysis and decision theory,
Part II: Markov chain Monte Carlo,
Part III: probability & convex optimisation,
Part VI: mixture, random fields, and hierarchical models.

Plenary talk I will have the honour of being a plenary speaker at SMAI 2019 (Biennalle Française des Mathématiques Appliquées et Industrielles), which will take place on 13-17 May 2019 in Guidel, Morbihan, France. More details soon.

Invited Position I will have the honour to hold an Invited Professor position at the Institut Henri Poincaré in Paris during the "Mathematics of Imaging" trimester (Jan. to April 2019). Please see the programme webpage for details and to register for the fantastic workshops and activities proposed.

© 2017 Marcelo Pereyra
Template design by Andreas Viklund / Best hosted at www.svenskadomaner.se