The Optimization and AI group works on the boundaries between optimization and learning, in order to enable data to guide the design of optimization algorithms, and enable optimization algorithms to learn and adapt to application-specific structures of problem instances. We work both on designing the next-generation of optimization algorithms, and on integrating AI and optimization in a tight loop to achieve improvements in a wide range of domains. Decision problems in many critical application domains---e.g., global supply chain and logistics, management, routing, logistics and transportation, the design and operation of the energy infrastructure, and hardware design---typically involve solving models with a very large number of decision variables, and parameters that are subject to high-dimensional uncertainty that is revealed over multiple time scales. We are actively engaged in solving such problems, with the goal of providing mathematical insights and efficient practical performance.
