We propose a discriminative algorithm learning an uncertainty function which preserves ordering of the input space induced by the con- ditional risk, and hence ...

We propose a discriminative algorithm learning an uncertainty function which preserves ordering of the input space induced by the conditional risk, and hence ...

In our paper we show: 1) What is the optimal c(x). 2) How to learn c(x) discriminatively. 2/2. On Discriminative Learning of Prediction Uncertainty.

This paper studies the problem of constructing robust classifiers when the training is plagued with uncertainty. The problem is posed as a Chance-Constrained ...

Jun 13, 2024 · Our objective is to compare the ability of both approaches to leverage information from various sources in an epistemic uncertainty aware ...

Discriminative theories frame language learning as a process of reducing uncertainty about the meaning of an utterance by discriminating informative from ...

In this paper, we developed a rigorous frequentist procedure for quantifying the uncertainty in predictions issued by deep learning models in a post-hoc fashion ...

This page provides an overview of our lab's work to date on uncertainty quantification, including approaches for the time-series setting.

The uncertainty in deep learning is explored to construct the prediction intervals and a special loss function is designed, which enables to learn uncertainty ...

Usable estimates of predictive uncertainty should (1) cover the true prediction targets with high probability, and (2) discriminate between high- and low- ...