OREGON STATE UNIVERSITY

You are here

Data-driven Decision-making

KEC 1007
Monday, March 31, 2014 - 8:45am to 10:00am
Speaker Information
Scott Sanner
NICTA and the Australian National University

Social media is connecting all information, the Internet is becoming more interactive and personalized, and every embedded system that impacts our lives -- from our daily commute to our consumer needs -- is becoming increasingly adaptive to our welfare and that of society. The wealth of structured, real-time information that we can leverage for computationally automated decision-making in these settings is unprecedented and requires a fundamental reassessment of how we approach these problems from a data-driven perspective. In this talk I will outline my contributions and lessons learned from working on a variety of commercial and industrial data-driven decision-making problems ranging from social media recommendation to traffic control. I will conclude with a vision that unifies learning, inference, and optimal sequential decision-making and suggest that between the two extremes of the most general theoretical frameworks and existing specialized solutions, there lies a vast unexplored space of models and algorithms that promise to shape the future of how computation interacts with the world.

Speaker Bio

Scott Sanner is a Principal Researcher at NICTA Canberra (a research lab intended to incubate startups and foster collaboration between academia and industry) and Adjunct Faculty at the Australian National University where his research spans a broad range of topics from the data-driven fields of machine learning and information retrieval to the decision-driven fields of artificial intelligence and operations research. Scott has applied the analytic and algorithmic tools from these fields to diverse application areas such as social media recommendation, preference learning, and transport optimization. Scott earned a PhD in Computer Science from the University of Toronto, an MS in Computer Science from Stanford, and a double BS in Computer Science and Electrical and Computer Engineering from Carnegie Mellon. During his studies, Scott interned with numerous research institutions including Microsoft Research Cambridge, Toyota Technological Institute at Chicago, Sun Microsystems Research Labs, Lockheed Martin, and the National Cancer Institute.