Saved in:
Bibliographic Details
Main Authors: Bairaktari, Konstantina, Nguyen, Huy L.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.23000
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912609756774400
author Bairaktari, Konstantina
Nguyen, Huy L.
author_facet Bairaktari, Konstantina
Nguyen, Huy L.
contents 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 interpolates between two established calibration error notions, one with known exponential sample complexity and one with polynomial sample complexity for calibrating a given predictor. Our algorithm can calibrate any given predictor for the entire range of interpolation, except for one endpoint, using only a polynomial number of samples. At the other endpoint, we achieve nearly optimal dependence on the error parameter, improving upon previous work. A key technical contribution is a novel application of adaptive data analysis with high adaptivity but only logarithmic overhead in the sample complexity.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23000
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sample-efficient Multiclass Calibration under $\ell_{p}$ Error
Bairaktari, Konstantina
Nguyen, Huy L.
Machine Learning
Data Structures and Algorithms
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 interpolates between two established calibration error notions, one with known exponential sample complexity and one with polynomial sample complexity for calibrating a given predictor. Our algorithm can calibrate any given predictor for the entire range of interpolation, except for one endpoint, using only a polynomial number of samples. At the other endpoint, we achieve nearly optimal dependence on the error parameter, improving upon previous work. A key technical contribution is a novel application of adaptive data analysis with high adaptivity but only logarithmic overhead in the sample complexity.
title Sample-efficient Multiclass Calibration under $\ell_{p}$ Error
topic Machine Learning
Data Structures and Algorithms
url https://arxiv.org/abs/2509.23000