Cover Image

Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dong, Andy, Özgür, Ayfer
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Leveraging Randomness in Model and Data Partitioning for Privacy Amplification
by: Dong, Andy, et al.
Published: (2025)

Trade-off Functions for DP-SGD with Subsampling based on Random Shuffling: Tight Upper and Lower Bounds
by: van Dijk, Marten, et al.
Published: (2026)

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

FlashDP: Private Training Large Language Models with Efficient DP-SGD
by: Wang, Liangyu, et al.
Published: (2025)

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

DP-SGD with weight clipping
by: Barczewski, Antoine, et al.
Published: (2023)

To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2024)

Universal Exact Compression of Differentially Private Mechanisms
by: Liu, Yanxiao, et al.
Published: (2024)

R+R:Understanding Hyperparameter Effects in DP-SGD
by: Morsbach, Felix, et al.
Published: (2024)

Tight Group-Level DP Guarantees for DP-SGD with Sampling via Mixture of Gaussians Mechanisms
by: Ganesh, Arun
Published: (2024)

Practical Differentially Private Hyperparameter Tuning with Subsampling
by: Koskela, Antti, et al.
Published: (2023)

Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD
by: Ertan, Murat Bilgehan, et al.
Published: (2026)

DP-SGD Without Clipping: The Lipschitz Neural Network Way
by: Bethune, Louis, et al.
Published: (2023)

On the Convergence of DP-SGD with Adaptive Clipping
by: Shulgin, Egor, et al.
Published: (2024)

Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
by: Cebere, Tudor, et al.
Published: (2024)

Closed-Form Bounds for DP-SGD against Record-level Inference
by: Cherubin, Giovanni, et al.
Published: (2024)

RQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization
by: Feng, Ce, et al.
Published: (2024)

PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance
by: Sha, Haichao, et al.
Published: (2023)

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

Lap2: Revisiting Laplace DP-SGD for High Dimensions via Majorization Theory
by: Mohammady, Meisam, et al.
Published: (2026)

It's Our Loss: No Privacy Amplification for Hidden State DP-SGD With Non-Convex Loss
by: Annamalai, Meenatchi Sundaram Muthu Selva
Published: (2024)

Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGD
by: Kalinin, Nikita P., et al.
Published: (2025)

Training generative models from privatized data
by: Reshetova, Daria, et al.
Published: (2023)

Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting
by: Schuchardt, Jan, et al.
Published: (2025)

DP-LDMs: Differentially Private Latent Diffusion Models
by: Liu, Michael F., et al.
Published: (2023)

DP-KAN: Differentially Private Kolmogorov-Arnold Networks
by: Kalinin, Nikita P., et al.
Published: (2024)

DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models
by: Sha, Haichao, et al.
Published: (2026)

Have it your way: Individualized Privacy Assignment for DP-SGD
by: Boenisch, Franziska, et al.
Published: (2023)

Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
by: Thudi, Anvith, et al.
Published: (2023)

DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling
by: Wei, Jianxin, et al.
Published: (2022)

Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimisation
by: Räisä, Ossi, et al.
Published: (2024)

DP-TLDM: Differentially Private Tabular Latent Diffusion Model
by: Zhu, Chaoyi, et al.
Published: (2024)

Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
by: Zhang, Xinwei, et al.
Published: (2023)

No More, No Less: Least-Privilege Language Models
by: Rauba, Paulius, et al.
Published: (2026)

Training Set Reconstruction from Differentially Private Forests: How Effective is DP?
by: Gorgé, Alice, et al.
Published: (2025)

An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses
by: Liang, Hao, et al.
Published: (2025)

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
by: Steinke, Thomas, et al.
Published: (2024)

LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models
by: Yang, Qin, et al.
Published: (2024)

DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation
by: Wei, Chengkun, et al.
Published: (2025)

Q-ShiftDP: A Differentially Private Parameter-Shift Rule for Quantum Machine Learning
by: Ngo, Hoang M., et al.
Published: (2026)