Score: 0

An $\tilde{O}$ptimal Differentially Private Learner for Concept Classes with VC Dimension 1

Published: May 10, 2025 | arXiv ID: 2505.06581v2

By: Chao Yan

Potential Business Impact:

Makes learning private and super fast.

Business Areas:
A/B Testing Data and Analytics

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 $\tilde{O}_{\varepsilon,\delta,\alpha,\delta}(\log^* d)$, nearly matching the lower bound of $\Omega(\log^* d)$ 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].

Country of Origin
🇺🇸 United States

Page Count
16 pages

Category
Computer Science:
Machine Learning (CS)