Accelerating Advanced Analytics - Arun Kumar

Event Details
  • Date/Time:
    • Tuesday February 2, 2016 - Wednesday February 3, 2016
      10:00 am - 10:59 am
  • Location: Klaus 1116 East and West
  • Phone:
  • URL:
  • Email:
  • Fee(s):
  • Extras:

Susie McClain


Summary Sentence: Accelerating Advanced Analytics - Arun Kumar

Full Summary: No summary paragraph submitted.

  • Arun Kumar Arun Kumar

Title: Accelerating Advanced Analytics


Advanced analytics -- the analysis of large and complex data with machine

learning (ML) -- is becoming ubiquitous, with a growing demand for

advanced analytics tools in the enterprise domains. However, there exist

several challenging bottlenecks in the end-to-end process of building and

deploying advanced analytics applications. My research focuses on

abstractions, algorithms, and systems to mitigate such bottlenecks and

accelerate advanced analytics from a data management standpoint.


In this talk, I will focus on my work on mitigating one such pervasive

bottleneck in the process of feature engineering for ML -- joins of

multiple tables. Many real-world datasets are multi-table, connected by

key-foreign key relationships, but almost all ML toolkits expect

single-table inputs. This forces data scientists to join all tables and

materialize a single table that collects all features. Alas, such joins

often cause the output to blow up in size, which slows down ML, increases

costs, and leads to data maintenance headaches. In my work, I show how it

is possible to mitigate these issues by "avoiding joins physically,"

i.e., pushing ML down through joins. This reduces runtime without

affecting accuracy. Going further, I apply statistical learning theory to

show how it is often possible to also "avoid joins logically," i.e.,

ignore entire tables outright without losing much accuracy, but achieving

significant runtime gains.



Arun Kumar is a Ph.D. candidate at the University of Wisconsin-Madison.

His primary research interests are in data management and its

intersection with machine learning. He is co-advised by Jeffrey Naughton

and Jignesh M. Patel, and has also worked closely with Christopher Re and

Xiaojin Zhu. Systems and ideas from his research have been shipped in

products by EMC, Oracle, Cloudera, and IBM. A paper co-authored by him

was accorded the Best Paper Award at ACM SIGMOD 2014. He was awarded the

Anthony C. Klug NCR Fellowship in database systems in 2015. He received

his M.S. from UW-Madison in 2011 and his B.Tech. from IIT Madras in 2009.


Additional Information

In Campus Calendar

College of Computing, School of Computer Science

Invited Audience
Undergraduate students, Faculty/Staff, Public, Graduate students
College of Computing, Georgia Tech, School of Computer Science
  • Created By: Birney Robert
  • Workflow Status: Published
  • Created On: Jan 21, 2016 - 10:38am
  • Last Updated: Apr 13, 2017 - 5:16pm