Consistent and Asymptotically Unbiased Estimation of Proper Calibration Errors

no code implementations • 14 Dec 2023 • Teodora Popordanoska, Sebastian G. Gruber, Aleksei Tiulpin, Florian Buettner, Matthew B. Blaschko

Proper scoring rules evaluate the quality of probabilistic predictions, playing an essential role in the pursuit of accurate and well-calibrated models.

A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models

no code implementations • 9 Oct 2023 • Sebastian G. Gruber, Florian Buettner

For example, natural language approaches cannot be transferred to image generation.

Image Generation Question Answering +2

Uncertainty Estimates of Predictions via a General Bias-Variance Decomposition

1 code implementation • 21 Oct 2022 • Sebastian G. Gruber, Florian Buettner

In this work we introduce a general bias-variance decomposition for proper scores, giving rise to the Bregman Information as the variance term.

Classification Out-of-Distribution Detection

Better Uncertainty Calibration via Proper Scores for Classification and Beyond

2 code implementations • 15 Mar 2022 • Sebastian G. Gruber, Florian Buettner

With model trustworthiness being crucial for sensitive real-world applications, practitioners are putting more and more focus on improving the uncertainty calibration of deep neural networks.