paper-with-me

홈 › Papers

Sample-efficient Multiclass Calibration under $\ell_{p}$ Error

2025-09-26 · Konstantina Bairaktari, Huy L. Nguyen arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.23000

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Top-label calibration and multiclass-to-binary reductions

2021-07-18 · ICLR 2022 4 · Chirag Gupta, Aaditya Ramdas

A multiclass classifier is said to be top-label calibrated if the reported probability for the predicted class -- the top-label -- is calibrated, conditioned on the top-label. This conditioning on the top-label is absent…

Decision Making

Optimal Multiclass U-Calibration Error and Beyond

2024-05-28 · Haipeng Luo, Spandan Senapati, Vatsal Sharan

We consider the problem of online multiclass U-calibration, where a forecaster aims to make sequential distributional predictions over $K$ classes with low U-calibration error, that is, low regret with respect to all bou…

Scalable Utility-Aware Multiclass Calibration

2025-10-29 · Mahmoud Hegazy, Michael I. Jordan, Aymeric Dieuleveut arxiv

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…

Verified Uncertainty Calibration

2019-09-23 · NeurIPS 2019 12 · Ananya Kumar, Percy Liang, Tengyu Ma

Applications such as weather forecasting and personalized medicine demand models that output calibrated probability estimates---those representative of the true likelihood of a prediction. Most models are not calibrated …

Weather Forecasting

Divide et Calibra: Multiclass Local Calibration via Vector Quantization

2026-05-20 · Cesare Barbera, Lorenzo Perini, Giovanni De Toni, Andrea Passerini 외 arxiv

Accurate and well-calibrated Machine Learning (ML) models are mandatory in high-stakes settings, yet effective multiclass calibration remains challenging: global approaches assume calibration errors are homogeneous acros…

Dimensionality Reduction