A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergences
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
We derive the optimal differential privacy (DP) parameters of a mechanism that satisfies a given level of Renyí differential privacy (RDP). Our result is based on the joint range of two f-divergences that underlie the approximate and the Renyi variations of differential privacy. We apply our result tó the moments accountant framework for characterizing privacy guarantees of stochastic gradient descent. When compared to the state-of-the-art, our bounds may lead to about 100 more stochastic gradient descent iterations for training deep learning models for the same privacy budget.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Privacy-preserving deep learning
Shokri, R., & Shmatikov, V. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813687 · Cited by 2,356
Mironov, I. (2017) · 2017 IEEE 30th Computer Security Foundations Symposium (CSF) · doi:10.1109/csf.2017.11 · Cited by 1,255 · cited 1×
“Instead of dealing with DP directly, the MA approach provides privacy guarantees in terms of Rényi differential privacy (RDP) [13] for which composition has a simple linear form.”
BackgroundBoosting and Differential Privacy
Dwork, C., Rothblum, G. N., & Vadhan, S. (2010) · 2010 IEEE 51st Annual Symposium on Foundations of Computer Science · doi:10.1109/focs.2010.12 · Cited by 784 · cited 3×
“[3] as a method to bypass advanced composition theorems [11, 12].”
BackgroundMethodSemi-supervised Knowledge Transfer for Deep Learning from Private Training Data
Papernot, N., Abadi, M., Erlingsson, Ú., Goodfellow, I., & Talwar, K. (2016) · arXiv · doi:10.48550/arxiv.1610.05755 · Cited by 492
The composition theorem for differential privacy
Kairouz, P., Oh, S., & Viswanath, P. (2017) · IEEE Transactions on Information Theory · doi:10.1109/tit.2017.2685505 · Cited by 408 · cited 3×
“[3] as a method to bypass advanced composition theorems [11, 12].”
BackgroundMethodSubsampled Rényi Differential Privacy and Analytical Moments Accountant
Wang, Y.-X., Balle, B., & Kasiviswanathan, S. (2018) · arXiv · doi:10.48550/arxiv.1808.00087 · Cited by 224
A General Approach to Adding Differential Privacy to Iterative Training Procedures
McMahan, H. B., Andrew, G., Erlingsson, U., Chien, S., Mironov, I., Papernot, N., & Kairouz, P. (2018) · arXiv · doi:10.48550/arxiv.1812.06210 · Cited by 126 · cited 1×
“, the implementation of [9] in the Google’s open-source TensorFlow Privacy framework [10].”
Background
Cited by
How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy
Ponomareva, N., Hazimeh, H., Kurakin, A., Xu, Z., Denison, C., McMahan, H. B., Vassilvitskii, S., Chien, S., & Thakurta, A. G. (2023) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.14649 · Cited by 166
“Rényi (O(q(es − 1)T ), δ), k slightly less than 1/2 Conversion from RDP to (ε, δ) via Lemma 1 (Asoodeh et al., 2020).”
BackgroundInfluentialThe distributed discrete gaussian mechanism for federated learning with secure aggregation
Kairouz, P., Liu, Z., & Steinke, T. (2021) · arXiv · doi:10.48550/arxiv.2102.06387 · Cited by 117
“In addition we have the following conversion lemma (Bun & Steinke, 2016; Canonne et al., 2020; Asoodeh et al., 2020) from concentrated DP to approximate DP.”
BackgroundPractical and private (deep) learning without sampling or shuffling
Kairouz, P., McMahan, B., Song, S., Thakkar, O., Thakurta, A., & Xu, Z. (2021) · arXiv · doi:10.48550/arxiv.2103.00039 · Cited by 52
EANA: Reducing Privacy Risk on Large-scale Recommendation Models
Ning, L., Chien, S., Song, S., Chen, M., Xue, Y., & Berlowitz, D. (2022) · Proceedings of the 16th ACM Conference on Recommender Systems · doi:10.1145/3523227.3546769 · Cited by 5
Metadata
- Authors
- Asoodeh, S., Liao, J., Calmon, F. P., Kosut, O., & Sankar, L.
- Venue
- 2020 IEEE International Symposium on Information Theory (ISIT)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 920-925
- OpenAlex
- W2998988480
- Cited by
- 28
- References
- 7
- FWCI
- 2.32
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergences. https://app.cochat.ai/papers/10.1109/isit44484.2020.9174015
- The paper
- Asoodeh, S., Liao, J., Calmon, F. P., Kosut, O., & Sankar, L. (2020). A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergences. 2020 IEEE International Symposium on Information Theory (ISIT). https://doi.org/10.1109/isit44484.2020.9174015
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.