Timezone: »

Conformal Prediction Under Covariate Shift
Ryan Tibshirani · Rina Barber · Emmanuel Candes · Aaditya Ramdas

Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #213

We extend conformal prediction methodology beyond the case of exchangeable data. In particular, we show that a weighted version of conformal prediction can be used to compute distribution-free prediction intervals for problems in which the test and training covariate distributions differ, but the likelihood ratio between the two distributions is known---or, in practice, can be estimated accurately from a set of unlabeled data (test covariate points). Our weighted extension of conformal prediction also applies more broadly, to settings in which the data satisfies a certain weighted notion of exchangeability. We discuss other potential applications of our new conformal methodology, including latent variable and missing data problems.

Author Information

Ryan Tibshirani (Carnegie Mellon University)
Rina Barber (University of Chicago)
Emmanuel Candes (Stanford University)
Aaditya Ramdas (CMU)

More from the Same Authors