The Importance of Being Smoothly Calibrated

• URL: http://arxiv.org/abs/2603.16015v1
• Date: Mon, 16 Mar 2026 23:50:02 GMT
• Title: The Importance of Being Smoothly Calibrated
• Abstract summary: We present a new omniprediction guarantee for smoothly predictors, for the class of all bounded proper losses.<n>The omniprediction error is bounded by the smooth calibration error of the predictor and the earth mover's distance from the benchmark.
• Score: 26.81026842833163
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent work has highlighted the centrality of smooth calibration [Kakade and Foster, 2008] as a robust measure of calibration error. We generalize, unify, and extend previous results on smooth calibration, both as a robust calibration measure, and as a step towards omniprediction, which enables predictions with low regret for downstream decision makers seeking to optimize some proper loss unknown to the predictor. We present a new omniprediction guarantee for smoothly calibrated predictors, for the class of all bounded proper losses. We smooth the predictor by adding some noise to it, and compete against smoothed versions of any benchmark predictor on the space, where we add some noise to the predictor and then post-process it arbitrarily. The omniprediction error is bounded by the smooth calibration error of the predictor and the earth mover's distance from the benchmark. We exhibit instances showing that this dependence cannot, in general, be improved. We show how this unifies and extends prior results [Foster and Vohra, 1998; Hartline, Wu, and Yang, 2025] on omniprediction from smooth calibration. We present a crisp new characterization of smooth calibration in terms of the earth mover's distance to the closest perfectly calibrated joint distribution of predictions and labels. This also yields a simpler proof of the relation to the lower distance to calibration from [Blasiok, Gopalan, Hu, and Nakkiran, 2023]. We use this to show that the upper distance to calibration cannot be estimated within a quadratic factor with sample complexity independent of the support size of the predictions. This is in contrast to the distance to calibration, where the corresponding problem was known to be information-theoretically impossible: no finite number of samples suffice [Blasiok, Gopalan, Hu, and Nakkiran, 2023].

Related papers

• Making and Evaluating Calibrated Forecasts [10.153382419318023]
  We introduce a perfectly truthful calibration measure for multi-class prediction tasks.<n>We mathematically prove and empirically verify that our calibration measure exhibits superior robustness.<n>This result addresses the non-robustness issue of binned ECE.
  arXiv  Detail & Related papers  (2025-10-07T19:11:03Z)
• A Perfectly Truthful Calibration Measure [9.916245963243542]
  A calibration measure quantifies how far a predictor is from perfect calibration.<n>We design a simple, perfectly and strictly truthful, sound and complete calibration measure in the batch setting.
  arXiv  Detail & Related papers  (2025-08-18T17:09:34Z)
• Measuring Informativeness Gap of (Mis)Calibrated Predictors [15.651406777700517]
  In many applications, decision-makers must choose between multiple predictive models that may all be miscalibrated.<n>Our framework strictly generalizes U-Calibration [KLST-23] and Decision Loss [HW-24], which compare a miscalibrated predictor to its calibrated counterpart.<n>Our second contribution is a dual characterization of the informativeness gap, which gives rise to a natural informativeness measure.
  arXiv  Detail & Related papers  (2025-07-16T10:01:22Z)
• Smooth Calibration and Decision Making [11.51844809748468]
  We show that post-processing an online predictor with $eps$ to calibration achieves $O(sqrtepsilon)$ ECE and CDL.<n>The optimal bound is non-optimal compared with existing online calibration algorithms.
  arXiv  Detail & Related papers  (2025-04-22T04:55:41Z)
• Orthogonal Causal Calibration [55.28164682911196]
  We develop general algorithms for reducing the task of causal calibration to that of calibrating a standard (non-causal) predictive model.<n>Our results are exceedingly general, showing that essentially any existing calibration algorithm can be used in causal settings.
  arXiv  Detail & Related papers  (2024-06-04T03:35:25Z)
• Towards Certification of Uncertainty Calibration under Adversarial Attacks [96.48317453951418]
  We show that attacks can significantly harm calibration, and thus propose certified calibration as worst-case bounds on calibration under adversarial perturbations.<n>We propose novel calibration attacks and demonstrate how they can improve model calibration through textitadversarial calibration training
  arXiv  Detail & Related papers  (2024-05-22T18:52:09Z)
• Calibration by Distribution Matching: Trainable Kernel Calibration Metrics [56.629245030893685]
  We introduce kernel-based calibration metrics that unify and generalize popular forms of calibration for both classification and regression. These metrics admit differentiable sample estimates, making it easy to incorporate a calibration objective into empirical risk minimization. We provide intuitive mechanisms to tailor calibration metrics to a decision task, and enforce accurate loss estimation and no regret decisions.
  arXiv  Detail & Related papers  (2023-10-31T06:19:40Z)
• Boldness-Recalibration for Binary Event Predictions [0.0]
  Ideally, probability predictions are (i) well calibrated, (ii) accurate, and (iii) bold, i.e., spread out enough to be informative for decision making. There is a fundamental tension between calibration and boldness, since calibration metrics can be high when predictions are overly cautious, i.e., non-bold. The purpose of this work is to develop a Bayesian model selection-based approach to assess calibration, and a strategy for boldness-recalibration.
  arXiv  Detail & Related papers  (2023-05-05T18:14:47Z)
• T-Cal: An optimal test for the calibration of predictive models [49.11538724574202]
  We consider detecting mis-calibration of predictive models using a finite validation dataset as a hypothesis testing problem. detecting mis-calibration is only possible when the conditional probabilities of the classes are sufficiently smooth functions of the predictions. We propose T-Cal, a minimax test for calibration based on a de-biased plug-in estimator of the $ell$-Expected Error (ECE)
  arXiv  Detail & Related papers  (2022-03-03T16:58:54Z)
• Localized Calibration: Metrics and Recalibration [133.07044916594361]
  We propose a fine-grained calibration metric that spans the gap between fully global and fully individualized calibration. We then introduce a localized recalibration method, LoRe, that improves the LCE better than existing recalibration methods.
  arXiv  Detail & Related papers  (2021-02-22T07:22:12Z)
• Unsupervised Calibration under Covariate Shift [92.02278658443166]
  We introduce the problem of calibration under domain shift and propose an importance sampling based approach to address it. We evaluate and discuss the efficacy of our method on both real-world datasets and synthetic datasets.
  arXiv  Detail & Related papers  (2020-06-29T21:50:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.