BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//128.220.13.64//NONSGML kigkonsult.se iCalcreator 2.20//
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Johns Hopkins Algorithms and Complexity
X-WR-CALDESC:
X-FROM-URL:https://www.cs.jhu.edu/~mdinitz/theory
X-WR-TIMEZONE:America/New_York
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:STANDARD
DTSTART:20211107T020000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20220313T020000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:ai1ec-278@www.cs.jhu.edu/~mdinitz/theory
DTSTAMP:20220124T030940Z
CATEGORIES:
CONTACT:
DESCRIPTION:Speaker: Grigory Yaroslavtsev\nAffiliation: Indiana University\
, Bloomington\nTitle: Advances in Hierarchical Clustering for Vector Data
\nAbstract:\nCompared to the highly successful flat clustering (e.g. k-mea
ns)\, despite its important role and applications in data analysis\, hiera
rchical clustering has been lacking in rigorous algorithmic studies until
late due to absence of rigorous objectives. Since 2016\, a sequence of wor
ks has emerged and gave novel algorithms for this problem in the general m
etric setting. This was enabled by a breakthrough by Dasgupta\, who introd
uced a formal objective into the study of hierarchical clustering.\nIn thi
s talk I will give an overview of our recent progress on models and scalab
le algorithms for hierarchical clustering applicable specifically to high-
dimensional vector data. I will first discuss various linkage-based algori
thms (single-linkage\, average-linkage) and their formal properties with r
espect to various objectives. I will then introduce a new projection-based
approximation algorithm for vector data. The talk will be self-contained
and doesn’t assume prior knowledge of clustering methods.\nBased on joint
works with Vadapalli (ICML’18) and Charikar\, Chatziafratis and Niazadeh (
AISTATS’19)
DTSTART;TZID=America/New_York:20190306T120000
DTEND;TZID=America/New_York:20190306T130000
SEQUENCE:0
SUMMARY:[Theory Seminar] Grigory Yaroslavtsev
URL:https://www.cs.jhu.edu/~mdinitz/theory/event/theory-seminar-grigory-yar
oslavtsev/
X-COST-TYPE:free
X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n\\n\\nSpeaker: Grig
ory Yaroslavtsev

\nAffiliation: Indiana University\, Bloomington

\nTitle: Advances in Hierarchical Clustering for Vector Data

\nAbs
tract:

\nCompared to the highly successful flat clustering (e.g. k-me
ans)\, despite its important role and applications in data analysis\, hier
archical clustering has been lacking in rigorous algorithmic studies until
late due to absence of rigorous objectives. Since 2016\, a sequence of wo
rks has emerged and gave novel algorithms for this problem in the general
metric setting. This was enabled by a breakthrough by Dasgupta\, who intro
duced a formal objective into the study of hierarchical clustering.

\n<
p>In this talk I will give an overview of our recent progress on models an
d scalable algorithms for hierarchical clustering applicable specifically
to high-dimensional vector data. I will first discuss various linkage-base
d algorithms (single-linkage\, average-linkage) and their formal propertie
s with respect to various objectives. I will then introduce a new projecti
on-based approximation algorithm for vector data. The talk will be self-co
ntained and doesn’t assume prior knowledge of clustering methods.\n
Based on joint works with Vadapalli (ICML’18) and Charikar\, Chatziafratis
and Niazadeh (AISTATS’19)

\n
END:VEVENT
END:VCALENDAR