English
Related papers

Related papers: Low-Degree Multicalibration

200 papers

Multicalibration extends classical calibration by requiring predictions to be unbiased over a rich collection of functions, encompassing both prediction slices and subpopulations. It has emerged as a powerful framework for fairness,…

Machine Learning · Statistics 2026-05-26 Hanxuan Ye , Hongzhe Li

This paper proposes the use of "multicalibration" to yield interpretable and reliable confidence scores for outputs generated by large language models (LLMs). Multicalibration asks for calibration not just marginally, but simultaneously…

Machine Learning · Statistics 2024-04-09 Gianluca Detommaso , Martin Bertran , Riccardo Fogliato , Aaron Roth

We study the problem of fair classification within the versatile framework of Dwork et al. [ITCS '12], which assumes the existence of a metric that measures similarity between pairs of individuals. Unlike earlier work, we do not assume that…

Machine Learning · Computer Science 2018-11-29 Michael P. Kim , Omer Reingold , Guy N. Rothblum

We identify and explore connections between the recent literature on multi-group fairness for prediction algorithms and the pseudorandomness notions of leakage-resilience and graph regularity. We frame our investigation using new variants…

Machine Learning · Computer Science 2025-07-10 Cynthia Dwork , Daniel Lee , Huijia Lin , Pranay Tankala

We provide a unifying framework for the design and analysis of multicalibrated predictors. By placing the multicalibration problem in the general setting of multi-objective learning -- where learning guarantees must hold simultaneously over…

Machine Learning · Computer Science 2023-09-21 Nika Haghtalab , Michael I. Jordan , Eric Zhao

Calibrating a multiclass predictor, that outputs a distribution over labels, is particularly challenging due to the exponential number of possible prediction values. In this work, we propose a new definition of calibration error that…

Machine Learning · Computer Science 2025-09-30 Konstantina Bairaktari , Huy L. Nguyen

Recent literature has seen a significant focus on building machine learning models with specific properties such as fairness, i.e., being non-biased with respect to a given set of attributes, calibration i.e., model confidence being aligned…

Machine Learning · Computer Science 2023-10-17 Anand Brahmbhatt , Vipul Rathore , Mausam , Parag Singla

Developing classification algorithms that are fair with respect to sensitive attributes of the data has become an important problem due to the growing deployment of classification algorithms in various social contexts. Several recent works…

Machine Learning · Computer Science 2020-04-16 L. Elisa Celis , Lingxiao Huang , Vijay Keswani , Nisheeth K. Vishnoi

We clarify what fairness guarantees we can and cannot expect to follow from unconstrained machine learning. Specifically, we characterize when unconstrained learning on its own implies group calibration, that is, the outcome variable is…

Machine Learning · Computer Science 2019-01-28 Lydia T. Liu , Max Simchowitz , Moritz Hardt

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

The goal of fairness in classification is to learn a classifier that does not discriminate against groups of individuals based on sensitive attributes, such as race and gender. One approach to designing fair algorithms is to use relaxations…

Machine Learning · Computer Science 2021-06-09 Kirtan Padh , Diego Antognini , Emma Lejal Glaude , Boi Faltings , Claudiu Musat

Being cautious is crucial for enhancing the trustworthiness of machine learning systems integrated into decision-making pipelines. Although calibrated probabilities help in optimal decision-making, perfect calibration remains unattainable,…

Machine Learning · Computer Science 2024-08-12 Mari-Liis Allikivi , Joonas Järve , Meelis Kull

A central goal of algorithmic fairness is to reduce bias in automated decision making. An unavoidable tension exists between accuracy gains obtained by using sensitive information (e.g., gender or ethnic group) as part of a statistical…

Machine Learning · Statistics 2020-02-03 Luca Oneto , Michele Donini , Amon Elders , Massimiliano Pontil

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

Probabilistic classifiers output a probability distribution on target classes rather than just a class prediction. Besides providing a clear separation of prediction and decision making, the main advantage of probabilistic models is their…

Machine Learning · Computer Science 2019-02-20 Juozas Vaicenavicius , David Widmann , Carl Andersson , Fredrik Lindsten , Jacob Roll , Thomas B. Schön

One prominent method of evaluating machine learning model trustworthiness is the notion of calibration. In the binary outcome setting, a probabilistic predictor is calibrated if outcomes are realized according to a model's distributional…

Machine Learning · Computer Science 2026-05-25 Jessica Finocchiaro , Victor Ganson , Drona Khurana

We propose an analysis in fair learning that preserves the utility of the data while reducing prediction disparities under the criteria of group sufficiency. We focus on the scenario where the data contains multiple or even many subgroups,…

Machine Learning · Statistics 2022-11-30 Changjian Shui , Gezheng Xu , Qi Chen , Jiaqi Li , Charles Ling , Tal Arbel , Boyu Wang , Christian Gagné

We revisit the foundations of fairness and its interplay with utility and efficiency in settings where the training data contain richer labels, such as individual types, rankings, or risk estimates, rather than just binary outcomes. In this…

Machine Learning · Computer Science 2025-05-23 Noga Amit , Omer Reingold , Guy N. Rothblum

Ensuring that classifiers are well-calibrated, i.e., their predictions align with observed frequencies, is a minimal and fundamental requirement for classifiers to be viewed as trustworthy. Existing methods for assessing multiclass…

Machine Learning · Computer Science 2025-10-30 Mahmoud Hegazy , Michael I. Jordan , Aymeric Dieuleveut

As machine learning models are increasingly deployed in high-stakes environments, ensuring both probabilistic reliability and prediction stability has become critical. This paper examines the interplay between classification calibration and…

Machine Learning · Computer Science 2026-03-17 Mustafa Cavus