Event Date
Event Date
Location
Mathematical Sciences Building 1147
Speaker: Vasilis Syrgkanis, Assistant Professor, Management Science and Engineering, Stanford University
Title: Inference on Optimal Policy Values and Other Irregular Functionals via Softmax Smoothing
Abstract: Constructing confidence intervals for the value of an (unknown) optimal treatment policy is a fundamental problem in causal inference. Insight into the optimal policy value can guide the development of reward-maximizing, individualized treatment regimes. However, because the functional that defines the optimal value is non-differentiable, standard semi-parametric approaches for performing inference fail to be directly applicable. Many existing works circumvent non-differentiability by making the unrealistic assumption of zero probability of treatment non-response, i.e. that every unit responds (either positively or negatively) to an assigned treatment. Further, works that don't circumvent this restriction rely on refitting nuisance models a number of times proportional to the sample size. In this paper, we construct and analyze a simple, softmax smoothing-based estimator for the value of an optimal treatment policy. Our estimator applies in both static and dynamic treatment regimes, only requires fitting a constant number of nuisance models, and is statistically efficient when there is zero probability of non-response to treatment. Also, while our estimator does not require making semi-parametric restrictions, it can exploit them when they exist. We further show how our softmax smoothing approach can be used to estimate general parameters that are specified as a maximum of scores involving nuisance components, and look at conditional Balke and Pearl bounds and L1 calibration error as salient examples.
Bio: Vasilis Syrgkanis is an Assistant Professor of Management Science and Engineering and (by courtesy) of Computer Science and Electrical Engineering at Stanford University. His research interests lie in the areas of machine learning, causal inference, econometrics, online and reinforcement learning, game theory, mechanism design and algorithm design. Until August 2022, he was a Principal Researcher at Microsoft Research, New England, where he was a member of the EconCS and StatsML groups and co-led the project on Automated Learning and Intelligence for Causation and Economics. He received his Ph.D. in Computer Science from Cornell University. His research has received best paper awards at several top tier machine learning and AI conferences (ACM EC, NeurIPS, COLT). He is the recipient of a 2022 Amazon Research Award, a 2023 Google Research Scholar Award, the 2023 Bodossaki Distinguished Young Scientist Award, a 2024 NSF CAREER Award and a 2025 Balakrishnan Early Career Award.