paper-with-me

Papers

Privacy Amplification of Iterative Algorithms via Contraction Coefficients

2020-01-17 · Shahab Asoodeh, Mario Diaz, Flavio P. Calmon

We investigate the framework of privacy amplification by iteration, recently proposed by Feldman et al., from an information-theoretic lens. We demonstrate that differential privacy guarantees of iterative mappings can be determined by a direct application of contraction coefficients derived from strong data processing inequalities for $f$-divergences. In particular, by generalizing the Dobrushin's contraction coefficient for total variation distance to an $f$-divergence known as $E_{\gamma}$-divergence, we derive tighter bounds on the differential privacy parameters of the projected noisy stochastic gradient descent algorithm with hidden intermediate updates.

📄 PDF Abstract BibTeX arXiv:2001.06546

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Doeblin Curves

2026-06-18 · Dongmin Lee, William Lu, Anuran Makur, Japneet Singh arxiv

Recent research on Doeblin coefficients has shed light on their usefulness as a multi-way generalization of the Dobrushin contraction coefficient for TV distance, in a separate vein from their classic role in the theory …

Contraction of $E_γ$-Divergence and Its Applications to Privacy

2020-12-20 · Shahab Asoodeh, Mario Diaz, Flavio P. Calmon

We investigate the contraction coefficients derived from strong data processing inequalities for the $E_\gamma$-divergence. By generalizing the celebrated Dobrushin's coefficient from total variation distance to $E_\gamm…

Local Differential Privacy Is Equivalent to Contraction of $E_γ$-Divergence

2021-02-02 · Shahab Asoodeh, Maryam Aliakbarpour, Flavio P. Calmon

We investigate the local differential privacy (LDP) guarantees of a randomized privacy mechanism via its contraction properties. We first show that LDP constraints can be equivalently cast in terms of the contraction coe…

Privacy Amplification by Iteration

2018-08-20 · Vitaly Feldman, Ilya Mironov, Kunal Talwar, Abhradeep Thakurta

Many commonly used learning algorithms work by iteratively updating an intermediate solution using one or a few data points in each iteration. Analysis of differential privacy for such algorithms often involves ensuring …

Contraction of Private Quantum Channels and Private Quantum Hypothesis Testing

2024-06-26 · Theshani Nuradha, Mark M. Wilde

A quantum generalized divergence by definition satisfies the data-processing inequality; as such, the relative decrease in such a divergence under the action of a quantum channel is at most one. This relative decrease is…

Fairness