Cover Image

Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms under Composition

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lebeda, Christian Janos, Regehr, Matthew, Kamath, Gautam, Steinke, Thomas
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Data Structures and Algorithms Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Bias-Accuracy-Privacy Trilemma for Statistical Estimation
by: Kamath, Gautam, et al.
Published: (2023)

The Discrete Gaussian for Differential Privacy
by: Canonne, Clément L., et al.
Published: (2020)

The Correlated Gaussian Sparse Histogram Mechanism
by: Lebeda, Christian Janos, et al.
Published: (2024)

Better Gaussian Mechanism using Correlated Noise
by: Lebeda, Christian Janos
Published: (2024)

Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent
by: Yu, Da, et al.
Published: (2022)

Individualized Privacy Accounting via Subsampling with Applications in Combinatorial Optimization
by: Ghazi, Badih, et al.
Published: (2024)

PLAN: Variance-Aware Private Mean Estimation
by: Aumüller, Martin, et al.
Published: (2023)

Scalable DP-SGD: Shuffling vs. Poisson Subsampling
by: Chua, Lynn, et al.
Published: (2024)

Continual Release of Densest Subgraphs: Privacy Amplification & Sublinear Space via Subsampling
by: Zhou, Felix
Published: (2025)

Robustness Implies Privacy in Statistical Estimation
by: Hopkins, Samuel B., et al.
Published: (2022)

Not All Learnable Distribution Classes are Privately Learnable
by: Bun, Mark, et al.
Published: (2024)

Better Differentially Private Approximate Histograms and Heavy Hitters using the Misra-Gries Sketch
by: Lebeda, Christian Janos, et al.
Published: (2023)

Weighted Fourier Factorizations: Optimal Gaussian Noise for Differentially Private Marginal and Product Queries
by: Lebeda, Christian Janos, et al.
Published: (2025)

Private Mean Estimation with Person-Level Differential Privacy
by: Agarwal, Sushant, et al.
Published: (2024)

The Broader Landscape of Robustness in Algorithmic Statistics
by: Kamath, Gautam
Published: (2024)

Optimal Differentially Private Sampling of Unbounded Gaussians
by: Iverson, Valentio, et al.
Published: (2025)

A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input
by: Mahpud, Bar, et al.
Published: (2025)

Privacy Filters are Captured by Residues: A Characterization of Free Natural Filters and the Cost of Adaptivity
by: Regehr, Matthew, et al.
Published: (2026)

Edgeworth Accountant: An Analytical Approach to Differential Privacy Composition
by: Wang, Hua, et al.
Published: (2022)

Privately Estimating Black-Box Statistics
by: Steinke, Günter F., et al.
Published: (2025)

Prediction with Expert Advice under Local Differential Privacy
by: Jacobsen, Ben, et al.
Published: (2025)

Privacy Amplification Persists under Unlimited Synthetic Data Release
by: Pierquin, Clément, et al.
Published: (2026)

Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy
by: Dvijotham, Krishnamurthy, et al.
Published: (2024)

Improved Regret in Stochastic Decision-Theoretic Online Learning under Differential Privacy
by: Wu, Ruihan, et al.
Published: (2025)

On Convex Optimization with Semi-Sensitive Features
by: Ghazi, Badih, et al.
Published: (2024)

How Private are DP-SGD Implementations?
by: Chua, Lynn, et al.
Published: (2024)

On the Price of Differential Privacy for Hierarchical Clustering
by: Deng, Chengyuan, et al.
Published: (2025)

Local Pan-Privacy for Federated Analytics
by: Feldman, Vitaly, et al.
Published: (2025)

Epsilon*: Privacy Metric for Machine Learning Models
by: Negoescu, Diana M., et al.
Published: (2023)

Privacy-Computation trade-offs in Private Repetition and Metaselection
by: Talwar, Kunal
Published: (2024)

Fast John Ellipsoid Computation with Differential Privacy Optimization
by: Li, Xiaoyu, et al.
Published: (2024)

High-Probability Bounds For Heterogeneous Local Differential Privacy
by: Aliakbarpour, Maryam, et al.
Published: (2025)

Balls-and-Bins Sampling for DP-SGD
by: Chua, Lynn, et al.
Published: (2024)

On Computing Pairwise Statistics with Local Differential Privacy
by: Ghazi, Badih, et al.
Published: (2024)

Differentially Private Bootstrap: New Privacy Analysis and Inference Strategies
by: Wang, Zhanyu, et al.
Published: (2022)

Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance
by: Gu, Xin, et al.
Published: (2023)

Learning from End User Data with Shuffled Differential Privacy over Kernel Densities
by: Wagner, Tal
Published: (2025)

CoinPress: Practical Private Mean and Covariance Estimation
by: Biswas, Sourav, et al.
Published: (2020)

A Smooth Binary Mechanism for Efficient Private Continual Observation
by: Andersson, Joel Daniel, et al.
Published: (2023)

Scaling up the Banded Matrix Factorization Mechanism for Differentially Private ML
by: McKenna, Ryan
Published: (2024)