BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Non-parametric regression for networks
DTSTART:20220429T153000
DTEND:20220429T170000
DTSTAMP:20260407T021115Z
UID:862e446e7e8d79fbb21d6c716af83fcfb361efc41f308eb1b506c786
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Ian Dryden\, Florida International University\nNetwork d
 ata are becoming increasingly available\, and so there is a need to develo
 p suitable methodology for statistical analysis. Networks can be represent
 ed as graph Laplacian matrices\, which are a type of manifold-valued data.
  Our main objective is to estimate a regression curve from a sample of gra
 ph Laplacian matrices conditional on a set of Euclidean covariates\, for e
 xample in dynamic networks where the covariate is time. We develop an adap
 ted Nadaraya-Watson estimator which has uniform weak consistency for estim
 ation using Euclidean and power Euclidean metrics.  \n \nWe apply the m
 ethodology to a study of peptide shape variation from molecular dynamics s
 imulations\, where networks are formed from the correlations between atoms
 . We investigate nonparametric regression of the networks versus time\, an
 d also versus a predictor measuring the change in size of the peptide. Fur
 ther applications are given to an email corpus to model smooth trends in m
 onthly networks and highlight anomalous networks. A final motivating appli
 cation is given in corpus linguistics\, which explores trends in an author
 ’s writing style over time based on word co-occurrence networks. \n \n
 This is joint work with Katie Severn and Simon Preston. \n\n\n 
LOCATION:https://epfl.zoom.us/j/66136073806
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR