Private Learning and Sanitization: Pure vs. Approximate Differential Privacy
Theory of Computing, Volume abs/1407.2674, Issue 1, 2016.
We compare the sample complexity of private learning [Kasiviswanathan et al. 2008] and sanitization~[Blum et al. 2008] under pure $\epsilon$-differential privacy [Dwork et al. TCC 2006] and approximate $(\epsilon,\delta)$-differential privacy [Dwork et al. Eurocrypt 2006]. We show that the sample complexity of these tasks under approxim...More
PPT (Upload PPT)