The limits of distribution-free conditional predictive inference
Abstract
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.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Aug 25, 2020
- Source ID
- 10.1093/imaiai/iaaa017
Entities
People
- Aaditya Ramdas
- Emmanuel Candès
- Rina Foygel Barber
- Ryan J. Tibshirani
Organizations
- Carnegie Mellon University
- National Science Foundation
- Office of Naval Research
- Stanford University
- University of Chicago