Structured Regularization Summer School - A. Montanari - 3/4 - 21/06/2017
236 views · Published 22 June 2017 · 1:32:20 · Indexed 27 October 2026
Channel: Institut Henri Poincaré · 2017 · Science & Technology
Andrea Montanari (Stanford): Matrix and graph estimation Abstract: Many statistics and unsupervised learning problems can be formalized as estimating a structured matrix or a graph from noisy or incomplete observations. These problems present a large variety of challenges, and an intriguing interplay between computational and statistical barriers. I will provide an introduction to recent work in the area, with an emphasis on general methods and unifying themes. 1) Random matrix theory and spectral methods. 2) The semidefinite programming approach to graph clustering. 3) Local algorithms and graphical models. The hidden clique problem. 4) Non-negative matrix factorization. ---------------------------------- Vous pouvez nous rejoindre sur les réseaux sociaux pour suivre nos actualités. Facebook : https://www.facebook.com/InstitutHenriPoincare/ Twitter : https://twitter.com/InHenriPoincare Instagram : https://www.instagram.com/instituthenripoincare/ LinkedIn : https://www.linkedin.com/company-beta/11054846/
More from this channel
-
29:47
10 ans du Groupe Calcul : Histoire du Calcul - Introduction
-
52:14
Gauss, Jacobi, Seidel, Richardson, Krylov: the Invention of Iterative Methods
-
55:33
Les "invariants arithmétiques" de H. Poincaré
-
1:08:53
Henri Poincaré, a founding father of the modern theory of PDEs
-
57:13
Sympletic topology from Poincaré to Gromov
-
57:35
Structural Realism, Then and Now
-
46:26
Poincaré inequalities in probability and geometric analysis
-
1:02:05
On the contributions of Henri Poincaré to modern geophysics...