BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//6.6.3//EN
TZID:America/New_York
X-WR-TIMEZONE:America/New_York
BEGIN:VEVENT
UID:637@fds.yale.edu
DTSTART;TZID=America/New_York:20241030T113000
DTEND;TZID=America/New_York:20241030T133000
DTSTAMP:20241029T142845Z
URL:https://fds.yale.edu/events/fds-colloquium-houman-owhadi-caltech/
SUMMARY:FDS Colloquium: Houman Owhadi (Caltech)\, "Co-discoveringÂ graphica
lÂ structure and functional relationships within data: A Gaussian Process
framework for connecting the dots"
DESCRIPTION:\nAbstract: \;Most scientific challenges can be framed into
one of the following three levels of complexity of function approximation
. \;\n\n\n\n\nType 1: Approximate an unknown function given input/outp
ut data. \;\n\n\n\nType 2: Consider a collection of variables and func
tions\, some of which are unknown\, indexed by the nodes and hyperedges of
a hypergraph (a generalized graph where edges can connect more than two v
ertices). Given partial observations of the variables of the hypergraph (s
atisfying the functional dependencies imposed by its structure)\, approxim
ate all the unobserved variables and unknown functions. \;\n\n\n\nType
3: Expanding on Type 2\, if the hypergraph structure itself is unknown\,
use partial observations of the variables of the hypergraph to discover it
s structure and approximate its unknown functions. \;\n\n\n\n\nExample
s of Type 2 problems include solving and learning (possibly stochastic) no
nlinear partial differential equations (PDEs)\, while Type 3 problems enco
mpass learning dependencies between variables in a mechanical system\, ide
ntifying chemical reaction networks\, and determining relationships betwee
n genes through a protein-signaling network. Although Gaussian Process (GP
) methods are sometimes perceived as a well-founded but old technology lim
ited to Type 1 curve fitting\, they can be generalized to an interpretable
framework for solving Type 2 and Type 3 problems\, all while maintaining
the simple and transparent theoretical and computational guarantees of ker
nel/optimal recovery methods.\n\n\n\nBio: Professor Owhadi's research conc
erns the exploration of interplays between numerical approximation\, stati
stical inference and learning \; from a game theoretic perspective. Wh
ereas the process of discovery is usually based on a combination of trial
and error\, \; insight and plain guesswork\, his research is motivated
by the facilitation/automation possibilities \; emerging from these i
nterplays.\n\n\n\nWebsite: https://www.cms.caltech.edu/people/owhadi\n
ATTACH;FMTTYPE=image/jpeg:https://fds.yale.edu/wp-content/uploads/2024/09/
Houman_Owhadi.jpeg
CATEGORIES:Colloquium
LOCATION:Yale Institute for Foundations of Data Science\, Kline Tower 13th
Floor\, Room 1327\, New Haven\, CT\, 06511\, United States
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Kline Tower 13th Floor\, Ro
om 1327\, New Haven\, CT\, 06511\, United States;X-APPLE-RADIUS=100;X-TITL
E=Yale Institute for Foundations of Data Science:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
DTSTART:20240310T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR