BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//128.220.36.25//NONSGML kigkonsult.se iCalcreator 2.26.9//
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-FROM-URL:https://www.clsp.jhu.edu
X-WR-TIMEZONE:America/New_York
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:STANDARD
DTSTART:20231105T020000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RDATE:20241103T020000
TZNAME:EST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240310T020000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RDATE:20250309T020000
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:ai1ec-22395@www.clsp.jhu.edu
DTSTAMP:20240329T023850Z
CATEGORIES;LANGUAGE=en-US:Seminars
CONTACT:
DESCRIPTION:
Abstract
\nRecursive call
s over recursive data are widely useful for generating probability distrib
utions\, and probabilistic programming allows computations over these dist
ributions to be expressed in a modular and intuitive way. Exact inference
is also useful\, but unfortunately\, existing probabilistic programming la
nguages do not perform exact inference on recursive calls over recursive d
ata\, forcing programmers to code many applications manually. We introduce
a probabilistic language in which a wide variety of recursion can be expr
essed naturally\, and inference carried out exactly. For instance\, probab
ilistic pushdown automata and their generalizations are easy to express\,
and polynomial-time parsing algorithms for them are derived automatically.
We eliminate recursive data types using program transformations related t
o defunctionalization and refunctionalization. These transformations are a
ssured correct by a linear type system\, and a successful choice of transf
ormations\, if there is one\, is guaranteed to be found by a greedy algori
thm. I will also describe the implementation of this language in two phase
s: first\, compilation to a factor graph grammar\, and second\, computing
the sum-product of the factor graph grammar.
\n
\nBiography
\nDavid Chiang (PhD\, University of Pennsylvania\, 2004) is an assoc
iate professor in the Department of Computer Science and Engineering at th
e University of Notre Dame. His research is on computational models for le
arning human languages\, particularly how to translate from one language t
o another. His work on applying formal grammars and machine learning to tr
anslation has been recognized with two best paper awards (at ACL 2005 and
NAACL HLT 2009). He has received research grants from DARPA\, NSF\, Google
\, and Amazon\, has served on the executive board of NAACL and the editori
al board of Computational Linguistics and JAIR\, and is currently on the e
ditorial board of Transactions of the ACL.
DTSTART;TZID=America/New_York:20221017T120000
DTEND;TZID=America/New_York:20221017T131500
LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street\, Baltimore\, MD 21218
SEQUENCE:0
SUMMARY:David Chiang (University of Notre Dame) “Exact Recursive Probabilis
tic Programming with Colin McDonald\, Darcey Riley\, Kenneth Sible (Notre
Dame) and Chung-chieh Shan (Indiana)”
URL:https://www.clsp.jhu.edu/events/david-chiang-university-of-notre-dame/
X-COST-TYPE:free
X-TAGS;LANGUAGE=en-US:2022\,Chiang\,October
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-22408@www.clsp.jhu.edu
DTSTAMP:20240329T023850Z
CATEGORIES;LANGUAGE=en-US:Seminars
CONTACT:
DESCRIPTION:Abstract
\nAI-powered appl
ications increasingly adopt Deep Neural Networks (DNNs) for solving many p
rediction tasks\, leading to more than one DNNs running on resource-constr
ained devices. Supporting many models simultaneously on a device is challe
nging due to the linearly increased computation\, energy\, and storage cos
ts. An effective approach to address the problem is multi-task learning (M
TL) where a set of tasks are learned jointly to allow some parameter shari
ng among tasks. MTL creates multi-task models based on common DNN architec
tures and has shown significantly reduced inference costs and improved gen
eralization performance in many machine learning applications. In this tal
k\, we will introduce our recent efforts on leveraging MTL to improve accu
racy and efficiency for edge computing. The talk will introduce multi-task
architecture design systems that can automatically identify resource-effi
cient multi-task models with low inference costs and high task accuracy.
div>\n
\n
Biography
\n
\n
\nHui Guan is an Assistant Professor in the
College
of Information and Computer Sciences (CICS) at the University o
f Massachusetts Amherst\, the flagship campus of the UMass system. She rec
eived her Ph.D. in Electrical Engineering from
North Carolina State Univer
sity in 2020. Her research lies in the intersection between mac
hine learning and systems\, with an emphasis on improving the speed\, scal
ability\, and reliability of machine learning through innovations in algor
ithms and programming systems. Her current research focuses on both algori
thm and system optimizations of deep multi-task learning and graph machine
learning.
\n\n \n
DTSTART;TZID=America/New_York:20221111T120000
DTEND;TZID=America/New_York:20221111T131500
LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street\, Baltimore\, MD 21218
SEQUENCE:0
SUMMARY:Hui Guan (University of Massachusetts Amherst) “Towards Accurate an
d Efficient Edge Computing Via Multi-Task Learning”
URL:https://www.clsp.jhu.edu/events/hui-guan-university-of-massachusetts-am
herst/
X-COST-TYPE:free
X-TAGS;LANGUAGE=en-US:2022\,Guan\,November
END:VEVENT
END:VCALENDAR