LGMLMar 16, 2020

Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning

arXiv:2003.07329v2280 citationsHas Code
AI Analysis

This addresses uncertainty calibration for deep learning practitioners, offering incremental improvements over existing methods.

The paper tackles the problem of post-hoc calibration for machine learning classifiers by introducing Mix-n-Match strategies, which achieve better data-efficiency and expressive power while maintaining classification accuracy, outperforming state-of-the-art solutions in most experiments.

This paper studies the problem of post-hoc calibration of machine learning classifiers. We introduce the following desiderata for uncertainty calibration: (a) accuracy-preserving, (b) data-efficient, and (c) high expressive power. We show that none of the existing methods satisfy all three requirements, and demonstrate how Mix-n-Match calibration strategies (i.e., ensemble and composition) can help achieve remarkably better data-efficiency and expressive power while provably maintaining the classification accuracy of the original classifier. Mix-n-Match strategies are generic in the sense that they can be used to improve the performance of any off-the-shelf calibrator. We also reveal potential issues in standard evaluation practices. Popular approaches (e.g., histogram-based expected calibration error (ECE)) may provide misleading results especially in small-data regime. Therefore, we propose an alternative data-efficient kernel density-based estimator for a reliable evaluation of the calibration performance and prove its asymptotically unbiasedness and consistency. Our approaches outperform state-of-the-art solutions on both the calibration as well as the evaluation tasks in most of the experimental settings. Our codes are available at https://github.com/zhang64-llnl/Mix-n-Match-Calibration.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes