aiqbench analysis
This paper proposes CoCP, a conformal prediction method that adapts both the center and radius of prediction intervals to heteroscedastic, skewed regression data, rather than using a fixed centering. The authors prove asymptotic conditional coverage and optimal interval length under consistency assumptions, and report tighter intervals in experiments. For ML practitioners, the key question is whether the gains hold on real datasets and at what computational cost, since the alternating optimization adds complexity over standard split-conformal methods.
Co-optimization for Adaptive Conformal Prediction
arXiv:2603.01719v2 Announce Type: replace-cross Abstract: In regression, conformal prediction often suffers from inefficiency under heteroscedasticity and skewness due to fixed, non-adaptive interval centering. We propose CoCP, a new method that parameterizes prediction intervals by a center $m(x)$ and a radius $h(x)$, and alternates between learning $h(x)$ via smooth quantile regression on folded residuals and refining $m(x)$ using a smooth interval loss. This corrects mis-centering and drives the interval toward high-density regions. Beyond finite-sample marginal validity via split-conformal calibration, we prove that CoCP also attains asymptotic conditional coverage and optimal interval length if the base estimators are consistent. Experiments demonstrate that CoCP yields tighter intervals and achieves improved empirical conditional-coverage reliability. Code is available at https://github.com/jjoeysu/cocp.
Abstract:In regression, conformal prediction often suffers from inefficiency under heteroscedasticity and skewness due to fixed, non-adaptive interval centering. We propose CoCP, a new method that parameterizes prediction intervals by a center $m(x)$ and a radius $h(x)$, and alternates between learning $h(x)$ via smooth quantile regression on folded residuals and refining $m(x)$ using a smooth interval loss. This corrects mis-centering and drives the interval toward high-density regions. Beyond finite-sample marginal validity via split-conformal calibration, we prove that CoCP also attains asymptotic conditional coverage and optimal interval length if the base estimators are consistent. Experiments demonstrate that CoCP yields tighter intervals and achieves improved empirical conditional-coverage reliability. Code is available at this https URL.
Machine Learning (stat.ML); Machine Learning (cs.LG)
arXiv:2603.01719 [stat.ML]
(or arXiv:2603.01719v2 [stat.ML] for this version)
https://doi.org/10.48550/arXiv.2603.01719 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 207 words