Minimax adaptive estimation in nonparametric Hidden Markov Models

Add to your list(s) Download to your calendar using vCal

• Yohann de Castro (Paris Sud - Orsay)
• Friday 21 October 2016, 16:00-17:00
• MR12, Centre for Mathematical Sciences, Wilberforce Road, Cambridge..

If you have a question about this talk, please contact Quentin Berthet.

In this talk, we review some recents results on nonparametric HMMs. We present and discuss the performances of the spectral estimator and the empirical least squares estimator in the nonparametric framework. In particular, this latter achieves minimax adaptive estimation of the emission laws (i.e. the conditional marginal distributions of the observations given the hidden states).

References :

(with É. Gassiat & C. Lacour) Minimax adaptive estimation of non-parametric Hidden Markov Models, Journal of Machine Learning Research, Volume 17, Issue 111, 2016, Pages 1-43.

(with É. Gassiat & S. Le Corff) Consistent estimation of the filtering and marginal smoothing distributions in nonparametric hidden Markov models

This talk is part of the Statistics series.

This talk is included in these lists:

• All CMS events
• All Talks (aka the CURE list)
• CMS Events
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• DPMMS Lists
• DPMMS info aggregator
• DPMMS lists
• Guy Emerson's list
• Hanchen DaDaDash
• Interested Talks
• MR12, Centre for Mathematical Sciences, Wilberforce Road, Cambridge.
• Machine Learning
• School of Physical Sciences
• Statistical Laboratory info aggregator
• Statistics
• Statistics Group
• bld31
• custom
• rp587

Note that ex-directory lists are not shown.