Presented By: Department of Statistics
Statistics Department Seminar Series: Blair Bilodeau, PhD candidate, Department of Statistical Sciences, University of Toronto
"Adaptive Sequential Decision Making and Uncertainty Quantification"
Abstract: One way to quantify the risks of deploying complex statistical methods is theoretical guarantees, yet statistical theory often relies on unverifiable assumptions and can therefore fail to explain performance in real-world settings. My research seeks out guarantees without such limitations across a wide range of statistical tasks, including inference, prediction, and decision making. In this talk, I will present two papers from this research program.
First, I will present https://arxiv.org/abs/2202.05100 (awarded an Oral designation at NeurIPS 2022, reserved for only 2% of submissions), where we study how to most efficiently select interventions in sequence to learn causal effects. We provide an adaptive method and corresponding guarantees: simultaneously optimal performance when benign causal structure exists and consistent estimation even when all causal assumptions fail. Second, I will present https://arxiv.org/abs/2109.10461, where we resolve the minimax rates for conditional density estimation in parametric and nonparametric classes. I will particularly focus on consequences of our results, including the first dimension-free KL risk bounds for generalized linear models, the first fast rates for KL risk with arbitrarily unbounded covariate spaces, and the first characterizations of KL risk for natural extensions of smoothness to conditional densities. Finally, I will discuss how these advances form a foundation of my future research: general adaptivity in non-stationary and partial-feedback settings.
Bio: Blair Bilodeau is a graduating PhD student in Statistical Sciences at the University of Toronto, advised by Daniel Roy. His PhD was funded by an NSERC Canada Graduate Scholarship and the Vector Institute. Blair’s work has been internationally recognized, including a Rising Star in Data Science award from the University of Chicago, an IMS Hannan Graduate Student Award, and a New York Academy of Science Best Poster Award. Open access versions of his publications and his full CV are available at http://www.blairbilodeau.ca.
First, I will present https://arxiv.org/abs/2202.05100 (awarded an Oral designation at NeurIPS 2022, reserved for only 2% of submissions), where we study how to most efficiently select interventions in sequence to learn causal effects. We provide an adaptive method and corresponding guarantees: simultaneously optimal performance when benign causal structure exists and consistent estimation even when all causal assumptions fail. Second, I will present https://arxiv.org/abs/2109.10461, where we resolve the minimax rates for conditional density estimation in parametric and nonparametric classes. I will particularly focus on consequences of our results, including the first dimension-free KL risk bounds for generalized linear models, the first fast rates for KL risk with arbitrarily unbounded covariate spaces, and the first characterizations of KL risk for natural extensions of smoothness to conditional densities. Finally, I will discuss how these advances form a foundation of my future research: general adaptivity in non-stationary and partial-feedback settings.
Bio: Blair Bilodeau is a graduating PhD student in Statistical Sciences at the University of Toronto, advised by Daniel Roy. His PhD was funded by an NSERC Canada Graduate Scholarship and the Vector Institute. Blair’s work has been internationally recognized, including a Rising Star in Data Science award from the University of Chicago, an IMS Hannan Graduate Student Award, and a New York Academy of Science Best Poster Award. Open access versions of his publications and his full CV are available at http://www.blairbilodeau.ca.
Explore Similar Events
-
Loading Similar Events...
