English

Towards Unbiased Calibration using Meta-Regularization

Machine Learning 2024-06-26 v3

Abstract

Model miscalibration has been frequently identified in modern deep neural networks. Recent work aims to improve model calibration directly through a differentiable calibration proxy. However, the calibration produced is often biased due to the binning mechanism. In this work, we propose to learn better-calibrated models via meta-regularization, which has two components: (1) gamma network (gamma-net), a meta learner that outputs sample-wise gamma values (continuous variable) for Focal loss for regularizing the backbone network; (2) smooth expected calibration error (SECE), a Gaussian-kernel based, unbiased, and differentiable surrogate to ECE that enables the smooth optimization of gamma-Net. We evaluate the effectiveness of the proposed approach in regularizing neural networks towards improved and unbiased calibration on three computer vision datasets. We empirically demonstrate that: (a) learning sample-wise gamma as continuous variables can effectively improve calibration; (b) SECE smoothly optimizes gamma-net towards unbiased and robust calibration with respect to the binning schemes; and (c) the combination of gamma-net and SECE achieves the best calibration performance across various calibration metrics while retaining very competitive predictive performance as compared to multiple recently proposed methods.

Keywords

Cite

@article{arxiv.2303.15057,
  title  = {Towards Unbiased Calibration using Meta-Regularization},
  author = {Cheng Wang and Jacek Golebiowski},
  journal= {arXiv preprint arXiv:2303.15057},
  year   = {2024}
}

Comments

20 pages. Accepted at TMLR: https://openreview.net/forum?id=Yf8iHCfG4W

R2 v1 2026-06-28T09:35:09.468Z