Cover Image

Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Şimşekli, Umut, Gürbüzbalaban, Mert, Yıldırım, Sinan, Zhu, Lingjiong
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Cryptography and Security Statistics Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Heavy-Tail Phenomenon in Decentralized SGD
by: Gurbuzbalaban, Mert, et al.
Published: (2022)

Rényi Differential Privacy for Heavy-Tailed SDEs via Fractional Poincaré Inequalities
by: Dupuis, Benjamin, et al.
Published: (2025)

Algorithmic Stability of Stochastic Gradient Descent with Momentum under Heavy-Tailed Noise
by: Dang, Thanh, et al.
Published: (2025)

Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tails
by: Sha, Haichao, et al.
Published: (2024)

GeoClip: Geometry-Aware Clipping for Differentially Private SGD
by: Gilani, Atefeh, et al.
Published: (2025)

Attack-Aware Noise Calibration for Differential Privacy
by: Kulynych, Bogdan, et al.
Published: (2024)

Optimal Regret of Bernoulli Bandits under Global Differential Privacy
by: Azize, Achraf, et al.
Published: (2025)

A Statistical Viewpoint on Differential Privacy: Hypothesis Testing, Representation and Blackwell's Theorem
by: Su, Weijie J.
Published: (2024)

Bayesian Adversarial Privacy
by: Bell, Cameron, et al.
Published: (2026)

Concentrated Differential Privacy for Bandits
by: Azize, Achraf, et al.
Published: (2023)

Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via $f$-Differential Privacy
by: Li, Xiang, et al.
Published: (2025)

Federated Transfer Learning with Differential Privacy
by: Li, Mengchu, et al.
Published: (2024)

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

An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise
by: Düngler, Johanna, et al.
Published: (2025)

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

Shifted Interpolation for Differential Privacy
by: Bok, Jinho, et al.
Published: (2024)

Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness
by: Chien, Eli, et al.
Published: (2024)

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

Beyond the Calibration Point: Mechanism Comparison in Differential Privacy
by: Kaissis, Georgios, et al.
Published: (2024)

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

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

Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Clipping Bias and Remedies
by: Li, Qiang, et al.
Published: (2024)

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

On Rate-Optimal Partitioning Classification from Observable and from Privatised Data
by: Csáji, Balázs Csanád, et al.
Published: (2023)

Generalization Bound and New Algorithm for Clean-Label Backdoor Attack
by: Yu, Lijia, et al.
Published: (2024)

Optimal Classification-based Anomaly Detection with Neural Networks: Theory and Practice
by: Zhou, Tian-Yi, et al.
Published: (2024)

Differentially Private Best-Arm Identification
by: Azize, Achraf, et al.
Published: (2024)

Differentially Private Manifold Denoising
by: Wu, Jiaqi, et al.
Published: (2026)

Differentially Private Sliced Inverse Regression: Minimax Optimality and Algorithm
by: Xia, Xintao, et al.
Published: (2024)

Some Targets Are Harder to Identify than Others: Quantifying the Target-dependent Membership Leakage
by: Azize, Achraf, et al.
Published: (2024)

On Privately Estimating a Single Parameter
by: Asi, Hilal, et al.
Published: (2025)

A Linear Approach to Data Poisoning
by: Flynn, Donald, et al.
Published: (2025)

On Differentially Private U Statistics
by: Chaudhuri, Kamalika, et al.
Published: (2024)

Sequential Membership Inference Attacks
by: Michel, Thomas, et al.
Published: (2026)

DP-SPRT: Differentially Private Sequential Probability Ratio Tests
by: Michel, Thomas, et al.
Published: (2025)

Optimal Survey Design for Private Mean Estimation
by: Chen, Yu-Wei, et al.
Published: (2025)

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

On the Privacy of Selection Mechanisms with Gaussian Noise
by: Lebensold, Jonathan, et al.
Published: (2024)

Privacy utility trade offs for parameter estimation in degree heterogeneous higher order networks
by: Mandal, Bibhabasu, et al.
Published: (2026)

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