BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Scalable Data Analytics: The Role of Stratified Data Sharding
DTSTART:20171107T110000
DTEND:20171107T120000
DTSTAMP:20260510T235012Z
UID:29b6a63181ff7886726572f6374fb1696671bb13117fc148ade9665a
CATEGORIES:Conferences - Seminars
DESCRIPTION:Professor Srinivasan Parthasarathy\, The Ohio State University
 \nWith the increasing popularity of structured data stores \, social netwo
 rks and Web 2.0 and 3.0 applications\, complex data formats\, such as tree
 s and graphs\, are becoming ubiquitous. Managing and processing such large
  and complex data stores\, on modern computational eco-systems\, to realiz
 e actionable information efficiently\, is daunting. In this talk I will be
 gin with discussing some of these challenges. Subsequently I will discuss 
 a critical element at the heart of this challenge relates to the sharding\
 , placement\, storage and access of such tera- and peta- scale data. In th
 is work we develop a novel distributed framework to ease the burden on the
  programmer and propose an agile and intelligent placement service layer a
 s a flexible yet unified means to address this challenge. Central to our f
 ramework is the notion of stratification which seeks to initially group st
 ructurally (or semantically) similar entities into strata. Subsequently st
 rata are partitioned within this eco-system according to the needs of the 
 application to maximize locality\, balance load\, minimize data skew or ev
 en take into account energy consumption. Results on several real-world app
 lications validate the efficacy and efficiency of our approach. (Notes: Jo
 int work with Y. Wang (Airbnb) and A. Chakrabarti (MSR))
LOCATION:BC 410 https://plan.epfl.ch/?room==BC%20410
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR