This week, we continue our introduction to faculty research topics. We encourage all faculty members and MS/PhD students to attend and hope these presentations would help students meet faculty members and get exposed to the full range of the research portfolio in our department. We feature the following speakers this week:
Presentation #1: "Research Overview for CDUX: Computing and Data Understanding at eXtreme Scale"
by Associate Professor Hank Childs
Abstract: The CDUX research group tackles a variety of problems in the areas of visualization, analysis, and high-performance computing. In this talk, I will describe some background that motivates our work and research directions that we are pursuing to solve them.
Presentation #2: "Understanding and Optimizing the Behavior of High-Performance Software"
by Associate Professor Boyana Norris
Abstract: This talk briefly overviews the research in the High Performance Computing Laboratory (HPCL), which pans several HPC areas including performance and power analysis, modeling and optimization, embeddable domain-specific languages for multi-target autotuning, and static source code analysis for detecting security vulnerabilities.
Presentation #3: "Addressing Real-world Societal Challenges: Advanced Game-Theoretic Models and Algorithms"
by Assistant Professor Thanh Nguyen
Abstract: This talk will cover my research in AI, with a focus on Multi-Agent Systems, for solving real-world societal problems, particularly in the areas of Sustainability, Public Safety and Security, Cyber- security, and Public Health. In these problems, strategic allocation of limited resources in an adversarial environment is an important challenge which involves complex human decision making, a variety of un- certainties, and exponential action spaces. In this talk, I will present my research in developing advanced game-theoretic models and algorithms for tactical allocation decisions in these problems. In particular, I will outline three main topics of my research: (i) learning new behavioral models of human decision-making for adversarial reasoning – I will discuss results from applying these models to both human subjects data from the lab and real-world data; (ii) developing game-theoretic algorithms, which address the challenge of deception in security — where weaknesses of learning algorithms are exploited by the attacker to mislead the defender; and (iii) designing scalable and robust game-theoretic algorithms, which address the challenge of uncertainty and exponential action and state spaces in complex societal problems. Finally, I will briefly introduce the real-world deployed application PAWS (Protection Assistant for Wildlife Security), which incorporates my models and algorithms, for wildlife protection.