Site Web DMA

Bannière DMA Site de l'ENS Site Paris Sciences et Lettres Site du CNRS Accueil

Séminaire Data de l'ENS

Horaires : Le mardi 08 novembre 2016, 12:00-14:00

Lieu : Room CONF IV (physic dpt)

What physics can tell us about inference?

Cristopher Moore (Santa Fe Institute - page personnelle)

There is a deep analogy between statistical inference and statistical physics; I will give a friendly introduction to both of these fields. I will then discuss phase transitions in two problems of interest to a broad range of data sciences: community detection in social and biological networks, and clustering of sparse high-dimensional data. In both cases, if our data becomes too sparse or too noisy, it suddenly becomes impossible to find the underlying pattern, or even tell if there is one. Physics both helps us locate these phase transiitons, and design optimal algorithms that succeed all the way up to this point. Along the way, I will visit ideas from computational complexity, random graphs, random matrices, and spin glass theory.


Autres séances du séminaire

45 rue d'Ulm - F 75230 PARIS cedex 05 | phone : (33) 1 44 32 20 49 | fax : (33) 1 44 32 20 69

Plan du site | Mentions légales | | Edition du site | Web site designed under SPIP