deep learning

Probabilistic latent variable models

Probabilistic machine learning for uncertainty-aware deep latent variable models

Uncertainty-aware deep learning in the real world

Uncertainty-aware supervised machine learning with deep neural networks for real-world applications

Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration

We address the problem of uncertainty cal-ibration and introduce a novel calibrationmethod, Parametrized Temperature Scaling(PTS). Standard deep neural networks typi-cally yield uncalibrated predictions, whichcan be transformed into calibrated confidencescores using post-hoc calibration methods.In this contribution, we demonstrate that theperformance of accuracy-preserving state-of-the-art post-hoc calibrators is limited by theirintrinsic expressive power. We generalizetemperature scaling by computing prediction-specific temperatures, parameterized by aneural network. We show with extensive ex-periments that our novel accuracy-preservingapproach consistently outperforms existingalgorithms across a large number of modelarchitectures, datasets and metrics.