BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:www.tcs.tifr.res.in/event/418
DTSTAMP:20230914T125923Z
SUMMARY:On the Power of Conditional Samples in Distribution Testing
DESCRIPTION:Speaker: Dr. Sourav Chakraborty (Chennai Mathematical Institute
(CMI)\nPlot No. H1 SIPCOT IT Park\nPadur PO\nSiruseri 603 103)\n\nAbstrac
t: \nAbstract: We define and examine the power of the conditional-sampling
oracle in the context of distribution-property testing. The conditional-s
ampling oracle for a discrete distribution $\\mu$ takes as input a subset
$S$ of the domain\, and outputs a random sample $i\\in S$ drawn according
to $\\mu$\, conditioned on $S$ (and independently of all prior samples). T
he conditional-sampling oracle is a natural generalization of the ordinary
sampling oracle in which $S$ always equals the whole domain.\n\nWe show t
hat with the conditional-sampling oracle\, testing uniformity\, testing id
entity to a known distribution\, and testing any label-invariant property
of distributions is easier than with the ordinary sampling oracle. On the
other hand\, we also show that for some distribution properties the sample
-complexity remains near-maximal even with conditional sampling.\n\nOne ca
n use conditional sampling for various real life problems also (this is a
joint work with Eldar Fischer\, Yonatan Goldhirsh and Arie Matsliah).\n
URL:https://www.tcs.tifr.res.in/web/events/418
DTSTART;TZID=Asia/Kolkata:20131107T160000
DTEND;TZID=Asia/Kolkata:20131107T170000
LOCATION:AG-80
END:VEVENT
END:VCALENDAR