University of California, Berkeley
20 novembre 2014 de 16 h 00 à 18 h 00 (heure de Montréal/HNE) Sur place
Statistical models in which the ambient dimension is of the same order or larger than the sample size arise frequently in different areas of science and engineering. Although high-dimensional models of this type date back to the work of Kolmogorov, they have been the subject of intensive study over the past decade, and have interesting connections to many branches of mathematics (including concentration of measure, random matrix theory, convex geometry, and information theory). In this talk, we provide a broad overview of the general area, including vignettes on phase transitions in high-dimensional graph recovery, and randomized approximations of convex programs.
AdresseCRM, UdeM, Pav. André-Aisenstadt, 2920, ch. de la Tour, salle 1360