Abstract Machine learning models always make a prediction, even when it is likely to be
inaccurate. This behavior should be avoided in many decision support applications, where …

Selective classification allows models to abstain from making predictions (eg, say" I don't
know") when in doubt in order to obtain better effective accuracy. While typical selective …

Crucial for building trust in deep learning models for critical real-world applications is
efficient and theoretically sound uncertainty quantification, a task that continues to be …

Many real-world multi-label prediction problems involve set-valued predictions that must
satisfy specific requirements dictated by downstream usage. We focus on a typical scenario …

The advent of large language models (LLMs) has dramatically advanced the state-of-the-art
in numerous natural language generation tasks. For LLMs to be applied reliably, it is …

Machine learning (ML) is a commonly employed computer-assisted tool for ECG diagnosis
with above 85% correct. However, the interpretability of the prediction has become a barrier …

A standard classification rule returns a single-valued prediction for any observation without a
confidence guarantee, which may result in severe consequences in many critical …

The integration of sophisticated deep learning models into critical domains, such as
healthcare, autonomous vehicles, and the legal system, is increasingly becoming a trend …

We present a simple yet effective method to implement the rejection option for a pre-trained
classifier. Our method is based on a sound mathematical framework, enjoys good …

Traditionally, doctors classify the sleep staging of patients by manually examining the
spectrogram of electroencephalogram (EEG) data at different time intervals. We propose a …