Enregistré dans:
Détails bibliographiques
Auteurs principaux: Tang, Zihao, Wang, Boyuan, Wen, Chuan, Teng, Jiaye
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2412.00653
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916501532966912
author Tang, Zihao
Wang, Boyuan
Wen, Chuan
Teng, Jiaye
author_facet Tang, Zihao
Wang, Boyuan
Wen, Chuan
Teng, Jiaye
contents Conformal prediction is widely adopted in uncertainty quantification, due to its post-hoc, distribution-free, and model-agnostic properties. In the realm of modern deep learning, researchers have proposed Feature Conformal Prediction (FCP), which deploys conformal prediction in a feature space, yielding reduced band lengths. However, the practical utility of FCP is limited due to the time-consuming non-linear operations required to transform confidence bands from feature space to output space. In this paper, we introduce Fast Feature Conformal Prediction (FFCP), which features a novel non-conformity score and is convenient for practical applications. FFCP serves as a fast version of FCP, in that it equivalently employs a Taylor expansion to approximate the aforementioned non-linear operations in FCP. Empirical validations showcase that FFCP performs comparably with FCP (both outperforming the vanilla version) while achieving a significant reduction in computational time by approximately 50x. The code is available at https://github.com/ElvisWang1111/FastFeatureCP
format Preprint
id arxiv_https___arxiv_org_abs_2412_00653
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Predictive Inference With Fast Feature Conformal Prediction
Tang, Zihao
Wang, Boyuan
Wen, Chuan
Teng, Jiaye
Machine Learning
Artificial Intelligence
Conformal prediction is widely adopted in uncertainty quantification, due to its post-hoc, distribution-free, and model-agnostic properties. In the realm of modern deep learning, researchers have proposed Feature Conformal Prediction (FCP), which deploys conformal prediction in a feature space, yielding reduced band lengths. However, the practical utility of FCP is limited due to the time-consuming non-linear operations required to transform confidence bands from feature space to output space. In this paper, we introduce Fast Feature Conformal Prediction (FFCP), which features a novel non-conformity score and is convenient for practical applications. FFCP serves as a fast version of FCP, in that it equivalently employs a Taylor expansion to approximate the aforementioned non-linear operations in FCP. Empirical validations showcase that FFCP performs comparably with FCP (both outperforming the vanilla version) while achieving a significant reduction in computational time by approximately 50x. The code is available at https://github.com/ElvisWang1111/FastFeatureCP
title Predictive Inference With Fast Feature Conformal Prediction
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2412.00653