Cover Image

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gu, Xin, Xiao, Yingtai, He, Guanlin, Bai, Jiamu, Kifer, Daniel, Maeng, Kiwan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Composition for Pufferfish Privacy
by: Bai, Jiamu, et al.
Published: (2026)

Accurate and Scalable Matrix Mechanisms via Divide and Conquer
by: He, Guanlin, et al.
Published: (2026)

ResidualPlanner+: a scalable matrix mechanism for marginals and beyond
by: Xiao, Yingtai, et al.
Published: (2023)

Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise
by: Wang, Puyu, et al.
Published: (2026)

Cocoon: A System Architecture for Differentially Private Training with Correlated Noises
by: Kim, Donghwan, et al.
Published: (2025)

LazyDP: Co-Designing Algorithm-Software for Scalable Training of Differentially Private Recommendation Models
by: Lim, Juntaek, et al.
Published: (2024)

Efficient and Private Marginal Reconstruction with Local Non-Negativity
by: Mullins, Brett, et al.
Published: (2024)

Towards Better Optimization For Listwise Preference in Diffusion Models
by: Bai, Jiamu, et al.
Published: (2025)

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

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature
by: Zhang, Yikuan, et al.
Published: (2026)

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

Proactive DP: A Multple Target Optimization Framework for DP-SGD
by: van Dijk, Marten, et al.
Published: (2021)

DP-λCGD: Efficient Noise Correlation for Differentially Private Model Training
by: Kalinin, Nikita P., et al.
Published: (2026)

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

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

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

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

Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simulation
by: Kim, Donghwan, et al.
Published: (2026)

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

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

Enhancing DP-SGD through Non-monotonous Adaptive Scaling Gradient Weight
by: Huang, Tao, et al.
Published: (2024)

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

From Privacy to Generalization: Linear Max-Information Bounds for DP-SGD
by: Lampert, Christoph H., et al.
Published: (2026)

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)

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

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

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)

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

Curvature-Informed SGD via General Purpose Lie-Group Preconditioners
by: Pooladzandi, Omead, et al.
Published: (2024)

Local Differential Privacy with Correlated Noise Achieves Central-DP Optimal Cost
by: Pathegama, Madhura, et al.
Published: (2026)

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

Differential Privacy in Two-Layer Networks: How DP-SGD Harms Fairness and Robustness
by: Xu, Ruichen, 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)

PoSafeNet: Safe Learning with Poset-Structured Neural Nets
by: Wong, Kiwan, et al.
Published: (2026)

Can SGD Handle Heavy-Tailed Noise?
by: Fatkhullin, Ilyas, et al.
Published: (2025)

Exact Risk Curves of signSGD in High-Dimensions: Quantifying Preconditioning and Noise-Compression Effects
by: Xiao, Ke Liang, et al.
Published: (2024)

Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
by: Vyas, Nikhil, et al.
Published: (2023)

SketchySGD: Reliable Stochastic Optimization via Randomized Curvature Estimates
by: Frangella, Zachary, et al.
Published: (2022)