Machine learning is becoming widely used in decision making, in domains ranging from personalized medicine and mobile health to online education and recommendation systems. While statistical machine learning traditionally excels at prediction problems, decision making requires answering questions that are counterfactual in nature, and ignoring this mismatch leads to unreliable decisions. As a consequence, our understanding of the algorithmic foundations for data-driven decision making is limited, and efficient algorithms are typically developed on an ad hoc basis. Can we bridge this gap and make decision making as easy as machine learning?

Focusing on the contextual bandit, a core problem in data-driven decision making, we bridge the gap by providing the first optimal and efficient reduction to supervised (parametric or nonparametric) regression. The algorithm allows users to seamlessly apply off-the-shelf machine learning models and methods to make decisions on the fly, and has been implemented in widely-used, industry-standard tools for decision making.

Our results advance a broader program to develop a universal algorithm design paradigm for data-driven decision making. I will close the talk by discussing challenges and opportunities in building such a framework, including efforts to extend our developments to reinforcement learning problems in large state spaces.

Bio: Dylan Foster is a postdoctoral fellow at the MIT Institute for Foundations of Data Science. He holds a PhD in computer science from Cornell University, where he was advised by Karthik Sridharan. He has received several awards, including the best paper award at COLT (2019), best student paper award at COLT (2018, 2019), Facebook PhD fellowship, and NDSEG PhD fellowship.

His research focuses on problems at the intersection of machine learning, statistics, and decision making.