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

Watch on YouTube

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