Publications

Uncertainty Estimation based on Geometric Separation

Published in Under review, 2023

In machine learning, accurately predicting the probability that a specific input is correct is crucial for risk management. This process, known as uncertainty (or confidence) estimation, is particularly important in mission-critical applications such as autonomous driving. In this work, we put forward a novel geometric-based approach for improving uncertainty estimations in machine learning models. Our approach involves using the geometric distance of the current input from existing training inputs as a signal for estimating uncertainty, and then calibrating this signal using standard post-hoc techniques. We demonstrate that our method leads to more accurate uncertainty estimations than recently proposed approaches through extensive evaluation on a variety of datasets and models. Additionally, we optimize our approach so that it can be implemented on large datasets in near real-time applications, making it suitable for time-sensitive scenarios.

Recommended citation: Chouraqui, G., Cohen, L., Einziger, G., & Leman, L. (2023). Uncertainty Estimation based on Geometric Separation. arXiv preprint arXiv:2301.04452. https://arxiv.org/abs/2301.04452

A Geometric Method for Improved Uncertainty Estimation in Real-time

Published in Uncertainty in Artificial Intelligence (UAI), 2022

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.

Recommended citation: Chouraqui, G., Cohen, L., Einziger, G., & Leman, L. (2022, August). A geometric method for improved uncertainty estimation in real-time. In Uncertainty in Artificial Intelligence (pp. 422-432). PMLR. https://arxiv.org/abs/2206.11562