Workshop on Systems and Analytics of Big Data, March 17, 2014

This event has ended and is now closed for registration.

Tremendous progress has been made in systems and analytics of big data, e.g. Hadoop/MapReduce, STORM. However, modern data analytics faces a confluence of growing challenges. First, the increasing data deluge in social networks, online retails, web pages, mobile data, etc creates the need to scale out across hundreds of thousands of commodity machines. Second, the complexity of data analytics has also grown to include sophisticated machine learning algorithm with data dependencies. Third, many systems process streaming data and have real time requirements.

We believe that this emerging field will benefit from close interaction among researchers and industry practitioners. This DIMACS workshop brings together academics and practitioners in computer systems, databases, networking, machine learning, and algorithms to share their research accomplishments and identify core problems on big data.

Topics of interest include but are not limited to the following:

  • Systems Issues related to large datasets: storage, data centers/clouds, streaming system, and architecture.
  • New programming model for big data beyond Hadoop/MapReduce, STORM, streaming languages
  • Streaming big data processing
  • Mining algorithms of big data in non-traditional formats (unstructured, semi-structured)
  • Scalable, distributed and parallel algorithms
  • Applications: mobile data, social network systems, smart grid, social media systems, scientific data mining, environmental, health analytics, financial analytics and smart cities.

DIMACS Center, CoRE Building, Rutgers University

Organizers:
Joseph Gonzalez, UC Berkeley
Daniel Hsu, Columbia University
Li Erran Li, Bell Labs, erranlli at gmail.com

Presented under the auspices of the Special Focus on Information Sharing and Dynamic Data Analysis and The Command, Control, and Interoperability Center for Advanced Data Analysis (CCICADA).

Workshop Program:

Monday, March 17, 2014

8:15 – 8:45 Registration and Breakfast – 4th Floor, Lounge, CoRE Building

8:45 – 9:00 Opening Remarks
Welcome Message from the organizers: Joseph Gonzalez, Daniel Hsu, and Li Erran Li

9:00 – 10:00 Low-latency Distributed Analytics in Naiad
Derek Murray, Microsoft Research Silicon Valley Lab

10:00 – 11:00 Counterfactual Reasoning and Learning Systems
Leon Bottou, Microsoft Research

11:00 – 11:30 Break

11:30 – 12:30 Large Scale Graph-Parallel Computation for Machine Learning: Applications and Systems
Joseph Gonzalez, Berkeley

12:30 – 1:20 Lunch Break

1:20 – 1:30 DIMACS Welcome
Gene Fiorini, Associate Director of DIMACS

1:30 – 2:30 Beyond Jeopardy! Adapting Watson to New Domains Using Distributional Semantics
Alfio Gliozzo

2:30 – 3:30 Machine Learning Meets the Crowd
Justin Moore, Facebook

3:30 – 4:00 Break

4:00 – 5:00 CloudCV: Computer Vision as a Cloud Service
Dhruv Batra, Virginia Tech

5:00 – 6:00 Panel on Systems and Analytics of Big Data

6:30 – 8:30 Dinner:
Panico’s Restaurant
103 Church Street
New Brunswick, NJ
(732)545-6100

Tuesday, March 18, 2014

8:30 – 9:00 Registration and Breakfast

9:00 – 10:00 MLbase: A User-Friendly System for Distributed Machine Learning
Ameet Talwalkar and Evan Sparks, Berkeley

10:00 – 11:00 Better Living with Randomness
Alex Smola, CMU

11:00 – 11:30 Break

11:30 – 12:30 The Thorn in the Side of Big Data: Too Few Artists
Christopher (Chris) Re, Stanford

12:30 – 1:30 Lunch

1:30 – 2:30 Computing on JetStream: Streaming Analytics in the Wide-Area
Matvey Arye, Princeton University

2:30 – 3:30 Posters and Lightening talks

Leave a comment

Your email address will not be published.


*


This site uses Akismet to reduce spam. Learn how your comment data is processed.