BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Bayesian Inference for Extended Latent Gaussian Models
DTSTART:20201120T161500
DTEND:20201120T180000
DTSTAMP:20260408T060105Z
UID:6d86a1df7d094fdaad5a54b0c7db1a173744272955b60f8825a000ea
CATEGORIES:Conferences - Seminars
DESCRIPTION:Alex Stringer\, University of Toronto\nWe define a novel class
  of additive regression models called Extended Latent Gaussian Models and 
 derive inference methodology for this class which scales to large datasets
  and is accompanied by theoretical guarantees.\nWe demonstrate this approa
 ch on several examples including spatial downscaling\, spatial proportiona
 l hazards regression with partial likelihood\, and Gaussian Process classi
 fication\, and demonstrate improved performance and scalability for existi
 ng Bayesian approaches to Generalized Linear Mixed and Additive Models.\nA
  notable feature of the method is the natural manner in which we account f
 or uncertainty in “smoothness” parameters\, a well-known and difficult
  problem which we address in this talk through both application and theory
 .\n 
LOCATION:zoom https://epfl.zoom.us/j/81419572433
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR