Data Science Seminar Series: Marcelo Pereyra

on the January 9, 2020

15:30 to 17:00
The Data Science Seminar Series bring high profile researchers to Université Grenoble Alpes to show the increasing role of data science in modern research. It is open to all researchers of Université Grenoble Alpes. For the last seminar of this year, we will welcome Marcelo Pereyra from Heriot-Watt University (Scotland).
Marcelo Pereyra from Heriot-Watt University (Scotland), will give a talk about “Bayesian inference and convex geometry: theory, methods, and algorithms”. The event will take place on Thursday 9 January at ENSIMAG building. The event will be followed by a coffee break.

Abstract

This talk presents an overview of some exciting new work that is developing at the fertile interface between imaging sciences, Bayesian statistics, and convex analysis. We will focus on new mathematical theory, methods, and algorithms for calibrating models and for performing uncertainty quantification in imaging inverse problems, and pay particular attention to the multidisciplinary aspects of the work. This will be illustrated with a range of examples related to medical, astronomical and hyperspectral imaging.


Related articles
https://arxiv.org/abs/1602.08590
https://arxiv.org/abs/1803.00889
https://arxiv.org/abs/1911.11709
https://arxiv.org/abs/1612.07471
https://arxiv.org/abs/1612.06149v1

Slides




Published on January 14, 2020

Practical informations

Lieu(x)


ENSIMAG - Amphi E
Campus universitaire de Grenoble