Cover Image

Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimisation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Räisä, Ossi, Jälkö, Joonas, Honkela, Antti
Format:	Preprint
Published:	2024
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

On Reliability of Efficient Membership Inference Vulnerability Evaluation
by: Jälkö, Joonas, et al.
Published: (2026)

Noise-Aware Differentially Private Variational Inference
by: Alrawajfeh, Talal, et al.
Published: (2024)

Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
by: Pradhan, Gauri, et al.
Published: (2025)

Accuracy-First Rényi Differential Privacy and Post-Processing Immunity
by: Räisä, Ossi, et al.
Published: (2025)

Efficient and Scalable Implementation of Differentially Private Deep Learning without Shortcuts
by: Beltran, Sebastian Rodriguez, et al.
Published: (2024)

Noise-Aware Differentially Private Regression via Meta-Learning
by: Räisä, Ossi, et al.
Published: (2024)

Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning
by: Tobaben, Marlon, et al.
Published: (2024)

$f$-Differential Privacy Filters: Validity and Approximate Solutions
by: Tran, Long, et al.
Published: (2026)

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

Privacy Leakage via Output Label Space and Differentially Private Continual Learning
by: Tobaben, Marlon, et al.
Published: (2024)

A Bias-Variance Decomposition for Ensembles over Multiple Synthetic Datasets
by: Räisä, Ossi, et al.
Published: (2024)

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

Empirical Comparison of Membership Inference Attacks in Deep Transfer Learning
by: Bai, Yuxuan, et al.
Published: (2025)

Mitigating Disparate Impact of Differentially Private Learning through Bounded Adaptive Clipping
by: Zhao, Linzh, et al.
Published: (2025)

Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners
by: Redberg, Rachel, et al.
Published: (2023)

Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement
by: Birrell, Jeremiah, et al.
Published: (2024)

Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?
by: Dong, Andy, et al.
Published: (2026)

Differentially Private In-Context Learning with Nearest Neighbor Search
by: Koskela, Antti, et al.
Published: (2025)

Gaussian DP for Reporting Differential Privacy Guarantees in Machine Learning
by: Gomez, Juan Felipe, et al.
Published: (2025)

Privacy Profiles for Private Selection
by: Koskela, Antti, et al.
Published: (2024)

Adaptive Batch Size for Privately Finding Second-Order Stationary Points
by: Liu, Daogao, et al.
Published: (2024)

Beyond One-Size-Fits-All: Neural Networks for Differentially Private Tabular Data Synthesis
by: Chen, Kai, et al.
Published: (2025)

Auditing Differential Privacy Guarantees Using Density Estimation
by: Koskela, Antti, et al.
Published: (2024)

Optimal Rates for Pure $\varepsilon$-Differentially Private Stochastic Convex Optimization with Heavy Tails
by: Lowy, Andrew
Published: (2026)

Differentially Private Subspace Fine-Tuning for Large Language Models
by: Zheng, Lele, et al.
Published: (2026)

Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy
by: Romijnders, Rob, et al.
Published: (2024)

Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
by: Tramèr, Florian, et al.
Published: (2022)

Delving into Differentially Private Transformer
by: Ding, Youlong, et al.
Published: (2024)

Differentially Private Attention Computation
by: Gao, Yeqi, et al.
Published: (2023)

Differentially Private Diffusion Models
by: Dockhorn, Tim, et al.
Published: (2022)

Privately Learning Decision Lists and a Differentially Private Winnow
by: Bun, Mark, et al.
Published: (2026)

Private and Communication-Efficient Federated Learning based on Differentially Private Sketches
by: Zhang, Meifan, et al.
Published: (2024)

Learning with Locally Private Examples by Inverse Weierstrass Private Stochastic Gradient Descent
by: Dufraiche, Jean, et al.
Published: (2026)

Differentially Private Random Feature Model
by: Liao, Chunyang, et al.
Published: (2024)

Differentially Private Conditional Independence Testing
by: Kalemaj, Iden, et al.
Published: (2023)

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

Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning
by: Liu, Xiao-Yang, et al.
Published: (2023)

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

Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification
by: Schuchardt, Jan, et al.
Published: (2024)

Differentially Private Training of Mixture of Experts Models
by: Tholoniat, Pierre, et al.
Published: (2024)