Efficient Online Set-valued Classification with Bandit Feedback

arXiv:2405.04393v1 Announce Type: cross
Abstract: Conformal prediction is a distribution-free method that wraps a given machine learning model and returns a set of plausible labels that contain the true label with a prescribed coverage rate. In practice, the empirical coverage achieved highly relies on fully observed label information from data both in the training phase for model fitting and the calibration phase for quantile estimation. This dependency poses a challenge in the context of online learning with bandit feedback, where …

abstract arxiv classification coverage cs.lg data distribution feedback free information labels machine machine learning machine learning model practice prediction rate returns set stat.ml true type