JOINT SEMINAR: Wilks Statistics Seminar and Korhammer Lecture Series
We consider the problem of distribution-free predictive inference, with the goal of producing predictive coverage guarantees that hold conditionally rather than marginally. Existing methods such as conformal prediction offer marginal coverage guarantees, where predictive coverage holds on average over all possible test points, but this is not sufficient for many practical applications where we would like to know that our predictions are valid for a given individual, not merely on average over a population. On the other hand, exact conditional inference guarantees are known to be impossible without imposing assumptions on the underlying distribution. In this work we aim to explore the space in between these two, and examine what types of relaxations of the conditional coverage property would alleviate some of the practical concerns with marginal coverage guarantees while still being possible to achieve in a distribution-free setting.
This is joint work with Emmanuel Candes, Aaditya Ramdas, and Ryan Tibshirani.
Rina Foygel Barber is an Associate Professor in the Department of Statistics at the University of Chicago. Before starting at U of C, she was a NSF postdoctoral fellow during 2012-13 in the Department of Statistics at Stanford University, supervised by Emmanuel Candès. She received a PhD in Statistics at the University of Chicago in 2012, advised by Mathias Drton and Nati Srebro, and a MS in Mathematics at the University of Chicago in 2009. Her research focuses on developing and analyzing estimation, inference, and optimization tools for structured high-dimensional data problems, particularly false discovery control in sparse regression problems. She also collaborates on modeling and optimization problems in image reconstruction for medical imaging.
This seminar is co-sponsored by S.S. Wilks Memorial Lecture series and the Korhammer Lecture Series