Research

CMAP Chairs present Eric Xing and Aymeric Dieuleveut, 18 Nov 2021

CMAP Research and Eductaion Chairs presents Eric Xing and Aymeric Dieuleveut, 18 Nov 2021.

On November 18th, the CMAP Research and Education Chair Department (École Polytechnique – IP Paris) is welcoming professor Eric Xing to the premises of the Ecole polytechnique. This face-to-face seminar will take place on Thursday 18th November from 10:40AM to 12:45PM, in the Louis Michel amphitheater (salle: 06 1040). 

Program:
– Aymeric Dieuleveut: “DoStoVoQ: Doubly Stochastic Voronoi Vector Quantization SGD for Federated Learning “
– 
Eric Xing: From Learning, to Meta Learning, to “Lego Learning” – theory, system, and applications

Please find below a detailed description of the speakers of this seminar.

Registration is free but mandatory.

Eric Xing

Eric Xing is Professor at CMU, Dean of Mohamed bin Zayed University of Artificial Intelligence (Mohamed bin Zayed University of Artificial Intelligence | MBZUAI), the wolrd’s first graduate level, research based artificial intelligence university. He was professor at Carnegie Mellon University and developed with his collaborator the Petuum framework for distributed machine learning. He has published over 200 peer-reviewed papers and has laid out his vision to train and enable a generation of industry and technology leaders.

Eric Xing is a recipient of the NSF Career Award, the Sloan Fellowship, the United States Air Force Young Investigator Award, the IBM Open Collaborative Research Award, and best paper awards in a number of premier conferences including UAI, ACL, EMNLP, SDM, ISMB. He is the Program Chair of ICML 2014.

Official webpage

Title of the talk: “From Learning, to Meta Learning, to “Lego Learning” – theory, system, and applications”

Aymeric Dieuleveut

Aymeric Dieuleveut is Assistant Professor in Statistics at École polytechnique. Aymeric Dieuleveut is also a Hi! PARIS Fellowships 2021 holder. More info here.

Official webpage

Title of the talk: “DoStoVoQ: Doubly Stochastic Voronoi Vector Quantization SGD for Federated Learning “