BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Statistical Inference for/via Covariance Operators - Victor Panare
 tos (EPFL - Ecole Polytechnique Fédérale de Lausanne)
DTSTART:20250507T143000Z
DTEND:20250507T153000Z
UID:TALK230470@talks.cam.ac.uk
DESCRIPTION:We consider the problem of comparing several samples of stocha
 stic processes with respect to their second-order structure. This task can
  be seen as an Analysis of Variance (ANOVA) of covariance operators\, and 
 arises naturally in functional data analysis. We formulate the problem bas
 ed on the nonlinear geometry of multimarginal transport\, where each covar
 iance can be identified with a a centred Gaussian process. By suitably con
 trasting the optimal multimarginal transport operators to the identity\, i
 t is seen that one can distinctly outperform existing tests\, with conside
 rable power even under local alternatives. This effect is seen to be genui
 nely functional\, and we conclude by showing how can can harness this func
 tional phenomenon in order to construct powerful tests in more traditional
  settings. Based on joint work with Valentina Masarotto (Leiden)\, Leonard
 o Santoro (EPFL)\, Yoav Zemel (EPFL)\, and Kartik Waghmare (ETH Z&uuml\;ri
 ch).&nbsp\;
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR