PeterHaasIBMMICDE Seminar: Peter Haas

Peter J. Haas is a Principal Research Staff Member at the IBM Almaden Research Center where, since 1987, he has worked at the interface of information management, applied probability, statistics, and computer simulation. He is an IBM Master Inventor and his ideas have been incorporated into products including IBM’s DB2 database system. He is also a Consulting Professor in the Department of Management Science and Engineering at Stanford University, teaching and conducting research in stochastic modeling and simulation. He is an ACM Fellow and has received a number of awards for his work on sampling-based exploration of massive datasets (ACM SIGMOD 10-Year Best Paper Award), the Splash platform for collaborative modeling and simulation, techniques for massive-scale matrix completion (2015 IBM Research Outstanding Innovation Award, 2011 NIPS Big Learning Workshop Best Paper), Monte Carlo methods for scalable querying and machine learning over massive uncertain data, and automated discovery of statistical features in databases with application to query optimization. He was President of the INFORMS Simulation Society from 2010 to 2012 and, in 2003, received its Outstanding Simulation Publication Award for his monograph on stochastic Petri nets. He serves on the editorial boards of Operations Research and ACM TOMACS, and was an Associate Editor for the VLDB Journal from 2007 to 2013. He is the author of roughly 150 conference publications, journal articles, and books.

Some Topics in Model-Data Ecosystems
4 – 6 p.m., Mon., Nov. 2, 2015
3725 BBB

Research around data management has begun to intertwine with research around predictive modeling and simulation in novel and interesting ways. Driving this trend is an increasing recognition that information contained in real-world data must be combined with information from domain experts, as embodied in first-principles simulation models, in order to enable robust decision making under uncertainty. This talk will outline some interesting new problems and results in this emerging research area, driven by our work both on pushing stochastic simulation into the database and on using information-integration technology to support collaborative modeling and simulation. Topics include simulation of database-valued Markov chains, transforming massive-scale time series, and optimal re-use of data in composite simulations.

This seminar is co-sponsored by the Department of Electrical Engineering and Computer Science, Computer Science and Engineering Division