Journée du Labex Bézout


Data Science and
Massive Data Analysis


On the campus of
ESIEE Paris, Ecole des Ponts ParisTech
and Université Paris-Est Marne-la-Vallée.
Cité Descartes, June 12th 2014

Program: morning session

At ESIEE in Amphi Marcel Dassault. The abstracts are online.

9h15
Arrival of attendees
9h30-9h40
Organisers
Labex Bézout
Foreword
9h40-10h30
Facebook AI Research / New York University
Learning hierarchical structures
10h30-11h00
coffee break
11h00-11h35
Criteo
Inside Criteo's Engine: Learning and predicting at scale
11h35-12h10
Università di Genova / MIT
Early stopping regularization
12h10-12h45
Université de Technologie de Compiègne
Learning Structure-Preserving Vector Representations of Objects from Open-Domain Relational Data
12h45-14h10
déjeuner

Program: afternoon session

At ESIEE in Amphi Marcel Dassault. The abstracts are online.

14h10-14h45
LIGM, Université Paris Est Marne-la-Vallée
Proximal methods: tools for solving inverse problems on a large scale
14h45-15h20
INRIA / ENS
Beyond stochastic gradient descent for large-scale machine learning
15h20-15h50
coffee break
15h50-16h25
Amazon
How Amazon leverages massive data sets in retail, web services and devices
16h25-17h00
Télécom ParisTech
Distributed optimization algorithms for multi-agent systems
17h00-18h30
cocktail

Organisers:

Laurent Najman, A3SI team, LIGM, ESIEE Paris.

Guillaume Obozinski, Imagine group, A3SI team, LIGM, Ecole des Ponts - ParisTech.

The laboratoire d'excellence Bézout  focusses on the extremely active research areas at the interface between mathematics and computer science. It includes all the members of three laboratories of the PRES UPE:

It also includes a few other scientific leading figures. Together, they represent more than 200 active researchers (including PhD students).

These laboratories are located in Marne-La-Vallée and Créteil.