BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Minimax adaptive estimation in nonparametric Hidden Markov Models 
 - Yohann de Castro (Paris Sud - Orsay)
DTSTART:20161021T150000Z
DTEND:20161021T160000Z
UID:TALK67487@talks.cam.ac.uk
CONTACT:Quentin Berthet
DESCRIPTION:In this talk\, we review some recents results on nonparametric
  HMMs. We present and discuss the performances of the spectral estimator a
 nd the empirical least squares estimator in the nonparametric framework. I
 n particular\, this latter achieves minimax adaptive estimation of the emi
 ssion laws (i.e. the conditional marginal distributions of the observation
 s given the hidden states). \n\nReferences : \n\n(with É. Gassiat & C. La
 cour) Minimax adaptive estimation of non-parametric Hidden Markov Models\,
  Journal of Machine Learning Research\, Volume 17\, Issue 111\, 2016\, Pag
 es 1-43.\n\n(with É. Gassiat & S. Le Corff) Consistent estimation of the 
 filtering and marginal smoothing distributions in nonparametric hidden Mar
 kov models
LOCATION:MR12\, Centre for Mathematical Sciences\, Wilberforce Road\, Camb
 ridge.
END:VEVENT
END:VCALENDAR