Thursday, September 13, 2018
TIME: 12:00 - 1:00 pm
PLACE: RMCIC Panther Hollow Conference Room, 4th Floor
SPEAKER: Pulkit Grover, CMU
TITLE: Reliable Computing Using Crappy Nodes
Can one compute reliably using unreliable elements? The question was first raised by von Neumann in 1956, but has received increased attention recently. In the past 5 years, our team has developed novel techniques that merge classical theory of error-correction coding with computing for machine-learning and scientific computing problems in large distributed systems. In this talk, I want to quickly overview these theoretical results, and spend time on our (preliminary) experimental validation, including development of a new platform -- CREDENCE -- that enables apples-to-apples comparison of various reliable computation strategies.
This is joint work largely with Malhar Chaudhari, Sanghamitra Dutta, Haewon Jeong, Soummya Kar, Tze Meng Low, Utsav Sheth, and Yaoqing Yang, at CMU, and Viveck Cadambe at Penn State.
Pulkit Grover (Ph.D. UC Berkeley'10, B.Tech, M. Tech IIT Kanpur) is an associate professor at CMU. His main contributions to science are towards developing and experimentally validating a new theory of information (fundamental limits, practical designs) for efficient and reliable communication, computing, sensing, and control, e.g. by incorporating computing system and circuit models. To apply these ideas to a variety of problems including novel biomedical systems, his lab works extensively with system and device engineers, neuroscientists, and doctors. Pulkit received the 2010 best student paper award at IEEE Conference on Decision and Control; the 2011 Eli Jury Dissertation Award from UC Berkeley; the 2012 Leonard G. Abraham best journal paper award from the IEEE ComSoc; a 2014 NSF CAREER award; a 2015 Google Research Award; the 2018 Joel and Rut Spira Excellence in Teaching Award, and a 2018 inaugural award from the Chuck Noll Foundation for Brain Injury Research. He presented an ISIT’17 tutorial on "coded computing," an emerging science of computing in presence of faults, delays, errors. He's learning how to play the sax and enjoys his free time with his wife, Kristen, and son, Utsah.
SDI / ISTC SEMINAR QUESTIONS?
Karen Lindenfelser, 86716, or visit www.pdl.cmu.edu/SDI/