English
Related papers

Related papers: The Sample Complexity of Multicalibration

200 papers

We present bounds for the finite sample error of sequential Monte Carlo samplers on static spaces. Our approach explicitly relates the performance of the algorithm to properties of the chosen sequence of distributions and mixing properties…

Computation · Statistics 2022-08-19 Joe Marion , Joseph Mathews , Scott C. Schmidler

When randomized ensembles such as bagging or random forests are used for binary classification, the prediction error of the ensemble tends to decrease and stabilize as the number of classifiers increases. However, the precise relationship…

Probability · Mathematics 2019-05-01 Miles E. Lopes

We study the sample complexity of multiclass prediction in several learning settings. For the PAC setting our analysis reveals a surprising phenomenon: In sharp contrast to binary classification, we show that there exist multiclass…

Machine Learning · Computer Science 2016-04-19 Amit Daniely , Sivan Sabato , Shai Ben-David , Shai Shalev-Shwartz

Multi-distribution learning extends agnostic Probably Approximately Correct (PAC) learning to the setting in which a family of $k$ distributions, $\{D_i\}_{i\in[k]}$, is considered and a classifier's performance is measured by its error…

Machine Learning · Computer Science 2025-06-24 Chicheng Zhang , Yihan Zhou

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

Machine learning models have traditionally been developed under the assumption that the training and test distributions match exactly. However, recent success in few-shot learning and related problems are encouraging signs that these models…

Machine Learning · Statistics 2020-10-15 James Lucas , Mengye Ren , Irene Kameni , Toniann Pitassi , Richard Zemel

Probabilistic classifiers output confidence scores along with their predictions, and these confidence scores should be calibrated, i.e., they should reflect the reliability of the prediction. Confidence scores that minimize standard metrics…

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

Calibrated probabilistic classifiers are models whose predicted probabilities can directly be interpreted as uncertainty estimates. It has been shown recently that deep neural networks are poorly calibrated and tend to output overconfident…

Machine Learning · Statistics 2022-10-17 Teodora Popordanoska , Raphael Sayer , Matthew B. Blaschko

A machine learning model is calibrated if its predicted probability for an outcome matches the observed frequency for that outcome conditional on the model prediction. This property has become increasingly important as the impact of machine…

Machine Learning · Computer Science 2025-02-25 Muthu Chidambaram , Rong Ge

Probability predictions are essential to inform decision making across many fields. Ideally, probability predictions are (i) well calibrated, (ii) accurate, and (iii) bold, i.e., spread out enough to be informative for decision making.…

Methodology · Statistics 2024-06-07 Adeline P. Guthrie , Christopher T. Franck

The fundamental theorem of statistical learning states that for binary classification problems, any Empirical Risk Minimization (ERM) learning rule has close to optimal sample complexity. In this paper we seek for a generic optimal learner…

Machine Learning · Computer Science 2014-05-13 Amit Daniely , Shai Shalev-Shwartz

We propose Rademacher complexity bounds for multiclass classifiers trained with a two-step semi-supervised model. In the first step, the algorithm partitions the partially labeled data and then identifies dense clusters containing $\kappa$…

Machine Learning · Statistics 2021-09-15 Yury Maximov , Massih-Reza Amini , Zaid Harchaoui

We study the sample complexity of online reinforcement learning in the general \hzyrev{non-episodic} setting of nonlinear dynamical systems with continuous state and action spaces. Our analysis accommodates a large class of dynamical…

Machine Learning · Computer Science 2026-03-02 Michael Muehlebach , Zhiyu He , Michael I. Jordan

Consider the problem of finding the best matching in a weighted graph where we only have access to predictions of the actual stochastic weights, based on an underlying context. If the predictor is the Bayes optimal one, then computing the…

Evaluation of clinical prediction models across multiple clusters, whether centers or datasets, is becoming increasingly common. A comprehensive evaluation includes an assessment of the agreement between the estimated risks and the observed…

Methodology · Statistics 2026-04-22 Lasai Barreñada , Bavo D. C. Campo , Laure Wynants , Ben Van Calster

Machine learning classifiers often produce probabilistic predictions that are critical for accurate and interpretable decision-making in various domains. The quality of these predictions is generally evaluated with proper losses, such as…

Machine Learning · Computer Science 2025-06-26 Eugène Berta , David Holzmüller , Michael I. Jordan , Francis Bach

Calibration is a critical property for establishing the trustworthiness of predictors that provide uncertainty estimates. Multicalibration is a strengthening of calibration which requires that predictors be calibrated on a potentially…

Machine Learning · Computer Science 2025-09-23 Nathan Derhake , Siddartha Devic , Dutch Hansen , Kuan Liu , Vatsal Sharan

The Expected Calibration Error (ece), the dominant calibration metric in machine learning, compares predicted probabilities against empirical frequencies of binary outcomes. This is appropriate when labels are binary events. However, many…

Machine Learning · Computer Science 2026-03-17 Michael Leznik

Multicalibration [HJKRR18] is an algorithmic fairness perspective that demands that the predictions of a predictor are correct conditional on themselves and membership in a collection of potentially overlapping subgroups of a population.…

Machine Learning · Computer Science 2025-11-10 Lunjia Hu , Haipeng Luo , Spandan Senapati , Vatsal Sharan