Sameer Agarwal

Sameer Agarwal, Graduate Student Algorithms, Machines and People Lab Email: sameerag@cs.berkeley.edu Operating Systems and Networking Group University of California, Berkeley Advisor: Ion Stoica

I am a third year PhD student working with Prof. Ion Stoica and Prof. Sam Madden on BlinkDB, a database that guarantees sub-second query latencies on unbounded data by trading-off on the accuracy of results. I also actively collaborate with Dr. Srikanth Kandula at Microsoft Research, Redmond on RoPE (Re-Optimizer for Parallel Execution). RoPE optimizes parallel executions by leveraging a variety of runtime/intermediate data statistics and has been under active deployment at Microsoft Bing. I completed my undergraduate education from the Department of Computer Science and Engineering at the Indian Institute of Technology, Guwahati in 2009 and was awarded the prestigious President of India Gold Medal.

I am supported by the Qualcomm Innovation Fellowship during 2012-13.

Education

• Ph.D., Computer Science, University of California, Berkeley, Fall 2009 - Continuing

• M.S., Computer Science, University of California, Berkeley, Spring 2012

• B.Tech. Computer Science and Engineering, Indian Institute of Technology, Guwahati, Spring 2009

Recent Publications

• Sameer Agarwal, Srikanth Kandula, Nicolas Bruno, Ming-Chuan Wu, Ion Stoica, Jingren Zhou. Re-optimizing Data Parallel Computing. USENIX NSDI 2012.

• Sameer Agarwal, Aurojit Panda, Barzan Mozafari, Samuel Madden, Ion Stoica. BlinkDB: Queries with Bounded Errors and Bounded Response Times on Very Large Data (Extended Abstract). USENIX NSDI 2012

• Nicolas Bruno, Sameer Agarwal, Srikanth Kandula, Bing Shi, Ming-Chuan Wu, Jingren Zhou. Recurring Job Optimization in Scope (Industrial Track). ACM SIGMOD 2012.

• Ganesh Ananthanarayanan, Sameer Agarwal, Srikanth Kandula, Albert Greenberg, Ion Stoica. Scarlett: Coping with Skewed Content Popularity in MapReduce Clusters. ACM EuroSys 2011.

• Sameer Agarwal, Mosharaf Chowdhury, Dilip Joseph, Ion Stoica. Lattice: A Scalable Layer-Agnostic Packet Classification Framework, UC Berkeley Technical Report UCB/EECS-2011-96, Aug. 2011.

• Sameer Agarwal, Dhruba Borthakur, Ion Stoica. Snapshots in the Hadoop Distributed File System. UC Berkeley Technical Report UCB/EECS Mar. 2011.

Selected Talks

• BlinkDB: Queries with Bounded Errors and Bounded Response Times on Very Large Data. AMPLab Retreat, Santa Cruz, CA, USA. May 17th, 2012

• BlinkDB: Queries with Bounded Errors and Bounded Response Times on Very Large Data. Qualcomm Research, San Diego, CA, USA. May 1st, 2012

• Re-optimizing Data Parallel Computing. USENIX NSDI, San Jose, CA, USA. April 27th, 2012.

• QuicksilverDB: Interactive Queries on Very Large Data. AMPLab Retreat, Lake Tahoe, CA, USA. Jan 11th, 2012

• The Data in the Datacenter. Microsoft Research, Redmond, WA, USA. August 11th, 2011.

• Analyzing the Network Health of Google's Datacenters. Google Inc., Mountain View, CA, USA. August 16th, 2010.

Teaching

• Fall 2010, EE 122: Introduction to Communication Networks with Prof. Scott Shenker

Miscellaneous

• My Erdos Number is 3 (me -> Albert G. Greenberg -> Janos Komlos -> Paul Erdos).

• My younger brother studies Computer Science at the Indian Institute of Technology, Kharagpur.