“Statistical Inference via Convex Optimization” book announced

Release date: April 2020

This authoritative book draws on the latest research to explore the interplay of high-dimensional statistics with optimization. Through an accessible analysis of fundamental problems of hypothesis testing and signal recovery, Anatoli Juditsky and Arkadi Nemirovski show how convex optimization theory can be used to devise and analyze near-optimal statistical inferences.

Published by Princeton University Press: Order/Infos here

3 New Ph.D. in the Team!

  • Gilles Bareilles (from ENSTA and MVA), who was an intern with Franck. His work deals with adaptive optimization methods for nonsmooth problems.
  • Yu-Guan Hsieh (from ENS and MVA), who was also an intern with Franck, Jérôme, and Panayotis. His work deals with variational analysis for machine learning.
  • Sélim Chraibi (from ENSIMAG), who was an intern with Peter Richtarik at KAUST. His work deals with practical large-scale and federated learning methods.

Welcome guys!

ANR “Jeune Chercheur” funding awarded to Franck

Franck was awarded a “Jeune Chercheur” (Young Researcher) funding from the ANR (French National Research Agency) for his project STROLL: Harnessing Structure in Optimization for Large-scale Learning. This competitive grant (<20% of success) will notably fund the Ph.D. of Gilles.