A matrix shuffling mechanism for edge-differentially private spectral clustering achieves Õ(1/n) misclassification error via privacy amplification and a unified Davis-Kahan plus margin analysis, outperforming Analyze Gauss and noisy power iteration.
arXiv preprint arXiv:2208.04591 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Replaces determinant growth with generalized Rayleigh quotient for rare switching in private linear bandits to control worst-direction volume despite non-monotonic design matrices from noise.
citing papers explorer
-
Differentially Private Spectral Graph Clustering: Balancing Privacy, Accuracy, and Efficiency
A matrix shuffling mechanism for edge-differentially private spectral clustering achieves Õ(1/n) misclassification error via privacy amplification and a unified Davis-Kahan plus margin analysis, outperforming Analyze Gauss and noisy power iteration.
-
When Determinants Are Not Enough: Private Rare Switching
Replaces determinant growth with generalized Rayleigh quotient for rare switching in private linear bandits to control worst-direction volume despite non-monotonic design matrices from noise.