Chao Gao: Statistical Optimality and Algorithms for Top-K Ranking - Lecture 2

Centre International de Rencontres Mathématiques
Centre International de Rencontres Mathématiques
357 بار بازدید - 3 سال پیش - CIRM VIRTUAL CONFERENCEIn the first
CIRM VIRTUAL CONFERENCE

In the first presentation, we will consider the top-K ranking problem. The statistical properties of two popular algorithms, MLE and rank centrality (spectral ranking) will be precisely characterized. In terms of both partial and exact recovery, the MLE achieves optimality with matching lower bounds. The spectral method is shown to be generally sub-optimal, though it has the same order of sample complexity as the MLE. Our theory also reveals the essentially only situation when the spectral method is optimal. This turns out to be the most favorable choice of skill parameter given the separation of the two groups.

Recorded during the meeting "​Meeting in mathematical Statistics" the December 18, 2020 by the Centre International de Rencontres Mathématiques (Marseille, France)
Filmmaker: Guillaume Hennenfent

Find this video and other talks given by worldwide mathematicians on CIRM's Audiovisual Mathematics Library: http://library.cirm-math.fr. And discover all its functionalities: - Chapter markers and keywords to watch the parts of your choice in the video - Videos enriched with abstracts, bibliographies, Mathematics Subject Classification - Multi-criteria search by author, title, tags, mathematical area
3 سال پیش در تاریخ 1399/10/22 منتشر شده است.
357 بـار بازدید شده
... بیشتر