REVIEW 9 cited by
Correlated Noise Mechanisms for Differentially Private Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Correlated Noise Mechanisms for Differentially Private Learning
read the original abstract
This monograph explores the design and analysis of correlated noise mechanisms for differential privacy (DP), focusing on their application to private training of AI and machine learning models via the core primitive of estimation of weighted prefix sums. While typical DP mechanisms inject independent noise into each step of a stochastic gradient (SGD) learning algorithm in order to protect the privacy of the training data, a growing body of recent research demonstrates that introducing (anti-)correlations in the noise can significantly improve privacy-utility trade-offs by carefully canceling out some of the noise added on earlier steps in subsequent steps. Such correlated noise mechanisms, known variously as matrix mechanisms, factorization mechanisms, and DP-Follow-the-Regularized-Leader (DP-FTRL) when applied to learning algorithms, have also been influential in practice, with industrial deployment at a global scale.
Forward citations
Cited by 9 Pith papers
-
Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise
First population risk bounds for KANs under mini-batch DP-SGD with correlated noise, using a new non-convex optimization analysis combined with stability-based generalization.
-
Improved Error Bounds for Pure Differentially Private Continual Counting via Matrix Factorization
Recursive matrix factorization from optimized low-dimensional bases yields pure-DP continual counting with MaxSE ≤ 0.0778 log^{3}_{2} n/ε^{2} and MeanSE ≤ 0.0710 log^{3}_{2} n/ε^{2}, plus Ω(log^{3} n) lower bounds for...
-
Local Differential Privacy with Correlated Noise Achieves Central-DP Optimal Cost
Correlated local noise under pure ε-DP achieves central-DP optimal estimation cost for sums up to arbitrarily small error.
-
CityOS: Privacy Architecture for Urban Sensing
CityOS is an edge runtime that enforces a three-tier privacy API for urban sensors: local raw data, differentially private single-location stats, and cross-location aggregates with per-user budgets enforced on devices.
-
Privacy, Prediction, and Allocation
Differentially private variants of individual and unit-level aid allocation strategies admit clean bounds on the tradeoffs between privacy, efficiency, and targeting precision across stochastic and distribution-free regimes.
-
Correlating Cross-Iteration Noise for DP-SGD using Model Curvature
Using Hessian eigenvalues from public data to design correlated noise for DP-SGD improves accuracy by 1–4% over current DP-MF methods.
-
From Privacy to Generalization: Linear Max-Information Bounds for DP-SGD
Proves linear max-information bound for DP-SGD and derives explicit PAC-Bayes generalization bounds with learnable prior and hyperparameter-controlled complexity term.
-
Limits of Personalizing Differential Privacy Budgets
For mean estimation, a simple thresholding operator on privacy budgets matches the performance of fully personalized differential privacy mechanisms up to constant factors.
-
Privacy, Prediction, and Allocation
Private variants of individual and unit-level aid allocation admit interpretable bounds trading privacy, efficiency, and targeting precision in stochastic and distribution-free settings.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.