Image de couverture de livre

Lap2: Revisiting Laplace DP-SGD for High Dimensions via Majorization Theory

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Mohammady, Meisam, Yang, Qin, Stout, Nicholas, Samreen, Ayesha, Wang, Han, Quinn, Christopher J, Hong, Yuan
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization
par: Yang, Qin, et autres
Publié: (2025)

DPI: Ensuring Strict Differential Privacy for Infinite Data Streaming
par: Feng, Shuya, et autres
Publié: (2023)

DP-SGD with weight clipping
par: Barczewski, Antoine, et autres
Publié: (2023)

Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergence
par: Feng, Shuya, et autres
Publié: (2024)

Rethinking the Security of DP-SGD: A Corrected Analysis of Differentially Private Machine Learning
par: Wang, Wenhao, et autres
Publié: (2026)

LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models
par: Yang, Qin, et autres
Publié: (2024)

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

To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling
par: Annamalai, Meenatchi Sundaram Muthu Selva, et autres
Publié: (2024)

FlashDP: Private Training Large Language Models with Efficient DP-SGD
par: Wang, Liangyu, et autres
Publié: (2025)

R+R:Understanding Hyperparameter Effects in DP-SGD
par: Morsbach, Felix, et autres
Publié: (2024)

On the Convergence of DP-SGD with Adaptive Clipping
par: Shulgin, Egor, et autres
Publié: (2024)

Have it your way: Individualized Privacy Assignment for DP-SGD
par: Boenisch, Franziska, et autres
Publié: (2023)

Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD
par: Ertan, Murat Bilgehan, et autres
Publié: (2026)

DP-SGD Without Clipping: The Lipschitz Neural Network Way
par: Bethune, Louis, et autres
Publié: (2023)

Balls-and-Bins Sampling for DP-SGD
par: Chua, Lynn, et autres
Publié: (2024)

How Private are DP-SGD Implementations?
par: Chua, Lynn, et autres
Publié: (2024)

Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
par: Cebere, Tudor, et autres
Publié: (2024)

Closed-Form Bounds for DP-SGD against Record-level Inference
par: Cherubin, Giovanni, et autres
Publié: (2024)

Privacy Enhanced PEFT: Tensor Train Decomposition Improves Privacy Utility Tradeoffs under DP-SGD
par: Kunwar, Pradip, et autres
Publié: (2026)

Revisiting Privacy-Utility Trade-off for DP Training with Pre-existing Knowledge
par: Zheng, Yu, et autres
Publié: (2024)

Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?
par: Dong, Andy, et autres
Publié: (2026)

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

Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
par: Thudi, Anvith, et autres
Publié: (2023)

Scalable DP-SGD: Shuffling vs. Poisson Subsampling
par: Chua, Lynn, et autres
Publié: (2024)

PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance
par: Sha, Haichao, et autres
Publié: (2023)

Trade-off Functions for DP-SGD with Subsampling based on Random Shuffling: Tight Upper and Lower Bounds
par: van Dijk, Marten, et autres
Publié: (2026)

Efficient Byzantine-Robust Privacy-Preserving Federated Learning via Dimension Compression
par: Qin, Xian, et autres
Publié: (2025)

DP-GENG : Differentially Private Dataset Distillation Guided by DP-Generated Data
par: Shi, Shuo, et autres
Publié: (2025)

Defense against Poisoning Attacks under Shuffle-DP
par: Wang, Siyi, et autres
Publié: (2026)

DP-S4S: Accurate and Scalable Select-Join-Aggregate Query Processing with User-Level Differential Privacy
par: Qiu, Yuan, et autres
Publié: (2026)

Differential Privacy with Higher Utility by Exploiting Coordinate-wise Disparity: Laplace Mechanism Can Beat Gaussian in High Dimensions
par: Muthukrishnan, Gokularam, et autres
Publié: (2023)

DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
par: Zhang, Xinwei, et autres
Publié: (2024)

Output Perturbation for Differentially Private Convex Optimization: Faster and More General
par: Lowy, Andrew, et autres
Publié: (2021)

High-Throughput Secure Multiparty Computation with an Honest Majority in Various Network Settings
par: Harth-Kitzerow, Christopher, et autres
Publié: (2022)

Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set
par: Fu, Jie, et autres
Publié: (2026)

Privacy by Postprocessing the Discrete Laplace Mechanism
par: Hillebrand, Quentin, et autres
Publié: (2026)

Onto-DP: Constructing Neighborhoods for Differential Privacy on Ontological Databases
par: Hayder, Yasmine, et autres
Publié: (2026)

Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
par: Zhang, Xinwei, et autres
Publié: (2023)

DP-SGD-Global-Adapt-V2-S: Triad Improvements of Privacy, Accuracy and Fairness via Step Decay Noise Multiplier and Step Decay Upper Clipping Threshold
par: Chilukoti, Sai Venkatesh, et autres
Publié: (2023)

A Failure-Free and Efficient Discrete Laplace Distribution for Differential Privacy in MPC
par: Tjuawinata, Ivan, et autres
Publié: (2025)