A Geometric Method for Improved Uncertainty Estimation in Real-time

TL;DR

This paper introduces a geometric approach for uncertainty estimation in machine learning classifiers that improves calibration accuracy and can be applied in real-time without retraining the model.

Contribution

The authors propose a novel geometric method for uncertainty estimation that enhances calibration and is suitable for real-time applications, outperforming recent approaches.

Findings

Better uncertainty calibration across multiple datasets and models.

Effective in near real-time scenarios.

Open-source implementation available.

Abstract

Machine learning classifiers are probabilistic in nature, and thus inevitably involve uncertainty. Predicting the probability of a specific input to be correct is called uncertainty (or confidence) estimation and is crucial for risk management. Post-hoc model calibrations can improve models' uncertainty estimations without the need for retraining, and without changing the model. Our work puts forward a geometric-based approach for uncertainty estimation. Roughly speaking, we use the geometric distance of the current input from the existing training inputs as a signal for estimating uncertainty and then calibrate that signal (instead of the model's estimation) using standard post-hoc calibration techniques. We show that our method yields better uncertainty estimations than recently proposed approaches by extensively evaluating multiple datasets and models. In addition, we also demonstrate the possibility of performing our approach in near real-time applications. Our code is available at our Github https://github.com/NoSleepDeveloper/Geometric-Calibrator.