BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//6.4.6.4.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:3569@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20141208T153000
DTEND;TZID=Europe/Paris:20141208T163000
DTSTAMP:20141123T143000Z
URL:https://www.i2m.univ-amu.fr/events/a-khaleghi-institut-curie-inference
-in-the-stationary-ergodic-framework/
SUMMARY:A. Khaleghi (Institut Curie): Inference in the Stationary Ergodic f
ramework -
DESCRIPTION: Inference in the Stationary Ergodic framework\n\nby Azadeh Kha
leghi (Institut Curie)\n\nAbstract: We consider two fundamental unsupervis
ed learning problems\\\, namely change point estimation and time-series cl
ustering\\\, in the case where the data are assumed to have been generated
by arbitrary\\\, unknown stationary ergodic process distributions. This i
s one of the weakest assumptions in statistics\\\, because it is more gene
ral than the parametric and model-based settings\\\, and it subsumes most
of the non-parametric frameworks considered for this class of problems. St
atistical analysis in the stationary ergodic framework is extremely challe
nging. In general\\\, rates of convergence (even of frequencies to respect
ive probabilities) are provably impossible to obtain for this class of pro
cesses. As a result\\\, given a pair of samples generated independently by
stationary ergodic process distributions\\\, it is provably impossible to
distinguish between the case where they are generated by the same process
or by two different ones. This in turn implies that such problems as time
se!\n ries clus\n t\nering with unknown number of clusters\\\, or online
change point detection\\\, cannot possibly admit consistent solutions. Thu
s\\\, a challenging task is to discover the problem formulations which adm
it consistent solutions in this general framework. Our main contribution i
s to constructively demonstrate that despite these theoretical impossibili
ty results\\\, natural formulations of the considered problems exist which
do indeed admit consistent solutions in this general framework. Specifica
lly\\\, we propose natural formulations as well as efficient algorithms wh
ich we further show to be asymptotically consistent under the assumption t
hat the process distributions are stationary ergodic. \n\n
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20141026T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR