B0935
Title: Approximate selective inference via maximum likelihood
Authors: Snigdha Panigrahi - University of Michigan (United States) [presenting]
Jonathan Taylor - Stanford University (United States)
Abstract: Several strategies have been developed recently to ensure valid inferences after model selection; some of these are easy to compute, while others fare better in terms of inferential power. We will address post-selection inference through approximate maximum likelihood estimation. The goal is to: (i) efficiently utilize hold-out information from selection with the aid of randomization, (ii) bypass expensive MCMC sampling from exact conditional distributions that are hard to evaluate in closed forms. At the core of our new method is the solution to a fairly simple, convex optimization problem in a few dimensions.