BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:8071@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20150522T140000
DTEND;TZID=Europe/Paris:20150522T150000
DTSTAMP:20241120T210015Z
URL:https://www.i2m.univ-amu.fr/evenements/cedric-beny-perimeter-institute
 -university-of-hanover-dimensionality-reduction-from-coarse-grained-fisher
 -metric/
SUMMARY: (...): Cédric Beny (Perimeter Institute/University of Hanover): D
 imensionality reduction from coarse-grained Fisher metric
DESCRIPTION:: Title: Dimensionality reduction from coarse-grained Fisher me
 tric\n\nAbstract: In physics\\\, one is often interested in describing onl
 y the large-scale\nproperties of complex statistical states. Renormalisati
 on is the\nproblem of finding the most relevant variables for that purpose
 . I\nwill show how a method developed in that context can be used for the\
 ndimensional reduction of abstract data. The approach yields a "PCA\nkerne
 l" whose diagonalisation amounts to finding the perturbations of\nthe empi
 rical distribution whose distinguishability is least affected\nby a certai
 n noise model (coarse-graining). This approach is invariant\nunder arbitra
 ry changes of coordinates. The kernel\\\, however\\\, requires\nthe calcul
 ation of a partition function which must be approximated. I\npresent two n
 umerical examples.
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20150329T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR