As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
When assessing uncertainty in model predictions, it is key to consider potential error patterns in some regions of the feature space. In this paper, we build on quantile regression to propose a new method to produce prediction intervals in regression tasks. It estimates a conditional quantile function of the residual variable given a specific representation. The method then adjusts the regressor’s prediction with an upper and lower conditional quantile prediction in order to produce an adaptive prediction interval for any new input. Further, we suggest an additional layer based on conformal prediction in order to provide coverage guarantees. Lastly, as distribution-free conditional coverage is impossible to achieve, we suggest a tree-based representation which displays patterns of undercoverage. This diagnostic tool aims to reveal which regions of the feature space are significantly less likely to have trustworthy prediction intervals. In order to prove their efficacy, our techniques are tested over various use cases and compared against four main baselines. Our methods empirically achieve the expected coverage and tend to produce shorter intervals.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.