Welcome to the Select Lab

Our main long-term research goal is developing efficient algorithms and methods for designing, analyzing, and controlling complex real-world systems. To achieve this goal, our research spans the entire spectrum from theoretical foundations to real-world applications.

Algorithmically, we focus on machine learning problems, where a system must sense the world, learn from experience and make effective long-term decisions. The techniques we develop encompass a wide range of topics, including probabilistic graphical models (e.g., Bayesian and Markov networks), active learning and value of information, distributed algorithms, probabilistic inference, decision making under uncertainty (e.g., partially observable Markov decision problems), online learning and game theory.

Our main applications are sensor networks, computer systems and robotics. Our current projects include real world deployments of sensors to monitor pollution in lakes and rivers, detect pathogens in our water distribution systems, build technology to help our aging and disabled population, and perform diagnosis in complex computer systems and networks.