English
Related papers

Related papers: Can a calibration metric be both testable and acti…

200 papers

Calibrated predictions are useful because their numerical values can be interpreted as probabilities. Calibration errors are therefore widely used to evaluate, compare, and tune probabilistic predictors. Recently, Haghtalab et al. (2024)…

Machine Learning · Computer Science 2026-05-19 Yuxuan Lu , Yifan Wu , Jason Hartline , Lunjia Hu

AI generated predictions increasingly inform decision making in critical tasks, and therefore must be trustworthy. One widely used measure of trustworthiness is calibration, which requires that the predictions match the true frequencies and…

Machine Learning · Computer Science 2026-05-19 Konstantina Bairaktari , Lunjia Hu , Huy L. Nguyen , Jonathan Ullman

Recent advances in machine learning have significantly improved prediction accuracy in various applications. However, ensuring the calibration of probabilistic predictions remains a significant challenge. Despite efforts to enhance model…

Machine Learning · Statistics 2025-08-05 Yan Sun , Pratik Chaudhari , Ian J. Barnett , Edgar Dobriban

Blasiok et al. [2023] proposed distance to calibration as a natural measure of calibration error that unlike expected calibration error (ECE) is continuous. Recently, Qiao and Zheng [2024] gave a non-constructive argument establishing the…

Machine Learning · Computer Science 2024-10-08 Eshwar Ram Arunachaleswaran , Natalie Collina , Aaron Roth , Mirah Shi

Calibration is a classical notion from the forecasting literature which aims to address the question: how should predicted probabilities be interpreted? In a world where we only get to observe (discrete) outcomes, how should we evaluate a…

Machine Learning · Computer Science 2025-09-03 Parikshit Gopalan , Lunjia Hu

Classifier calibration has received recent attention from the machine learning community due both to its practical utility in facilitating decision making, as well as the observation that modern neural network classifiers are poorly…

Machine Learning · Computer Science 2022-05-24 John Kirchenbauer , Jacob Oaks , Eric Heim

Calibration ensures that probabilistic forecasts meaningfully capture uncertainty by requiring that predicted probabilities align with empirical frequencies. However, many existing calibration methods are specialized for post-hoc…

Machine Learning · Computer Science 2023-11-01 Charles Marx , Sofian Zalouk , Stefano Ermon

In the face of dataset shift, model calibration plays a pivotal role in ensuring the reliability of machine learning systems. Calibration error (CE) is an indicator of the alignment between the predicted probabilities and the classifier…

Machine Learning · Computer Science 2023-12-15 Teodora Popordanoska , Gorjan Radevski , Tinne Tuytelaars , Matthew B. Blaschko

Neural network-based decisions tend to be overconfident, where their raw outcome probabilities do not align with the true decision probabilities. Calibration of neural networks is an essential step towards more reliable deep learning…

Machine Learning · Computer Science 2025-02-19 Geetanjali Bihani , Julia Taylor Rayz

Calibration is a frequently invoked concept when useful label probability estimates are required on top of classification accuracy. A calibrated model is a function whose values correctly reflect underlying label probabilities. Calibration…

Machine Learning · Computer Science 2024-12-03 Alireza Torabian , Ruth Urner

Calibration measures and reliability diagrams are two fundamental tools for measuring and interpreting the calibration of probabilistic predictors. Calibration measures quantify the degree of miscalibration, and reliability diagrams…

Machine Learning · Computer Science 2023-09-22 Jarosław Błasiok , Preetum Nakkiran

When providing probabilistic forecasts for uncertain future events, it is common to strive for calibrated forecasts, that is, the predictive distribution should be compatible with the observed outcomes. Several notions of calibration are…

Methodology · Statistics 2015-05-21 Christof Strähl , Johanna F. Ziegel

Model calibration aims to align confidence with prediction correctness. The Cross-Entropy (CE) loss is widely used for calibrator training, which enforces the model to increase confidence on the ground truth class. However, we find the CE…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Yuchi Liu , Lei Wang , Yuli Zou , James Zou , Liang Zheng

We study the fundamental question of how to define and measure the distance from calibration for probabilistic predictors. While the notion of perfect calibration is well-understood, there is no consensus on how to quantify the distance…

Machine Learning · Computer Science 2023-04-03 Jarosław Błasiok , Parikshit Gopalan , Lunjia Hu , Preetum Nakkiran

Calibration requires predictor outputs to be consistent with their Bayesian posteriors. For machine learning predictors that do not distinguish between small perturbations, calibration errors are continuous in predictions, e.g., smooth…

Machine Learning · Computer Science 2025-04-23 Jason Hartline , Yifan Wu , Yunran Yang

Confidence calibration has been dominated by the Expected Calibration Error (ECE), a linear metric that counts calibration offset equally regardless of the confidence level at which it occurs. We show that ECE can remain small even under…

Machine Learning · Computer Science 2026-05-06 Fernando Martin-Maroto , Nabil Abderrahaman , Gonzalo G. de Polavieja

The model uncertainty obtained by variational Bayesian inference with Monte Carlo dropout is prone to miscalibration. In this paper, different logit scaling methods are extended to dropout variational inference to recalibrate model…

Machine Learning · Computer Science 2020-06-23 Max-Heinrich Laves , Sontje Ihler , Karl-Philipp Kortmann , Tobias Ortmaier

Model uncertainty obtained by variational Bayesian inference with Monte Carlo dropout is prone to miscalibration. The uncertainty does not represent the model error well. In this paper, temperature scaling is extended to dropout variational…

Machine Learning · Computer Science 2019-11-19 Max-Heinrich Laves , Sontje Ihler , Karl-Philipp Kortmann , Tobias Ortmaier

Model calibration usually requires optimizing some parameters (e.g., temperature) w.r.t an objective function (e.g., negative log-likelihood). In this paper, we report a plain, important but often neglected fact that the objective function…

Machine Learning · Computer Science 2023-03-10 Yuli Zou , Weijian Deng , Liang Zheng

Most machine learning classifiers are designed to output posterior probabilities for the classes given the input sample. These probabilities may be used to make the categorical decision on the class of the sample; provided as input to a…

Machine Learning · Statistics 2024-08-07 Luciana Ferrer , Daniel Ramos