← Search

Erchi Wang

2 accepted papers

2025

Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning

ICML 2025poster

This paper studies the problem of differentially private empirical risk minimization (DP-ERM) for binary linear classification. We obtain an efficient $(\varepsilon,\delta)$-DP algorithm with an empirical zero-one risk bound of $\tilde{O}\left(\frac{1}{\gamma^2\varepsilon n} + \frac{|S_{\mathrm{o…

Cited by 0SourcePDFScholar
2025

Purifying Approximate Differential Privacy with Randomized Post-processing

NeurIPS 2025spotlight

We propose a framework to convert $(\varepsilon, \delta)$-approximate Differential Privacy (DP) mechanisms into $(\varepsilon', 0)$-pure DP mechanisms under certain conditions, a process we call ``purification.'' This algorithmic technique leverages randomized post-processing with calibrated noise t…

Cited by 0SourceScholar