Bernoulli Lecture - Statistical physics and statistical inference   05 October 2018

13:30 - 14:30
Room : BI A0 448

Lecturer

Marc Mézard, Ecole normale supérieure, PSL University


A major challenge of contemporary statistical inference is the large-scale limit, where one wants to discover the values of many hidden parameters, using large amount of data. In recent years, ideas from statistical physics of disordered systems, notably the cavity method, have helped to develop new algorithms for important inference problems, ranging from community detection to compressed sensing, machine learning (notably neural networks) and generalized linear regression. The talk will review these developments and explain how they can be used, together with the replica method, to identify phase transitions in benchmark statistical ensembles of inference problems.



Slides
Name University Dates of visit
Marc Mézard Ecole normale supérieure, PSL University 05/10/2018 - 05/10/2018
Total Guests : 1
Name University Dates of visit
Total Guests : 0