Enregistré dans:
Détails bibliographiques
Auteur principal: Yan, Chao
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.06581
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908469861285888
author Yan, Chao
author_facet Yan, Chao
contents We present the first nearly optimal differentially private PAC learner for any concept class with VC dimension 1 and Littlestone dimension $d$. Our algorithm achieves the sample complexity of $\tilde{O}_{\varepsilon,δ,α,δ}(\log^* d)$, nearly matching the lower bound of $Ω(\log^* d)$ proved by Alon et al. [STOC19]. Prior to our work, the best known upper bound is $\tilde{O}(VC\cdot d^5)$ for general VC classes, as shown by Ghazi et al. [STOC21].
format Preprint
id arxiv_https___arxiv_org_abs_2505_06581
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An $\tilde{O}$ptimal Differentially Private Learner for Concept Classes with VC Dimension 1
Yan, Chao
Machine Learning
Cryptography and Security
We present the first nearly optimal differentially private PAC learner for any concept class with VC dimension 1 and Littlestone dimension $d$. Our algorithm achieves the sample complexity of $\tilde{O}_{\varepsilon,δ,α,δ}(\log^* d)$, nearly matching the lower bound of $Ω(\log^* d)$ proved by Alon et al. [STOC19]. Prior to our work, the best known upper bound is $\tilde{O}(VC\cdot d^5)$ for general VC classes, as shown by Ghazi et al. [STOC21].
title An $\tilde{O}$ptimal Differentially Private Learner for Concept Classes with VC Dimension 1
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2505.06581