Distribution-Free, Risk-Controlling Prediction Sets

Add to your list(s) Download to your calendar using vCal

• Stephen Bates, University of California Berkeley
• Friday 05 February 2021, 16:00-17:00
• https://maths-cam-ac-uk.zoom.us/j/92821218455?pwd=aHFOZWw5bzVReUNYR2d5OWc1Tk15Zz09.

If you have a question about this talk, please contact Dr Sergio Bacallado.

To enable valid statistical inference in prediction tasks, we show how to generate set-valued predictions for black-box predictors that control the expected loss on future test points at a user-specified level. Our approach provides explicit finite-sample guarantees for any distribution by using a holdout set to calibrate the size of the prediction sets, generalizing conformal prediction to control more complex notions of error such as the false rejection rate. We demonstrate our procedure in five large-scale problems: (1) classification problems where some mistakes are more costly than others; (2) multi-label classification, where each observation has multiple associated labels; (3) classification problems where the labels have a hierarchical structure; (4) image segmentation, where we wish to predict a set of pixels containing an object of interest; and (5) protein structure prediction.

This talk is part of the Statistics series.

This talk is included in these lists:

• https://maths-cam-ac-uk.zoom.us/j/92821218455?pwd=aHFOZWw5bzVReUNYR2d5OWc1Tk15Zz09
• All CMS events
• All Talks (aka the CURE list)
• CMS Events
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• DPMMS Lists
• DPMMS info aggregator
• DPMMS lists
• Guy Emerson's list
• Hanchen DaDaDash
• Interested Talks
• Machine Learning
• School of Physical Sciences
• Statistical Laboratory info aggregator
• Statistics
• Statistics Group
• bld31
• custom
• rp587

Note that ex-directory lists are not shown.