Copertina

When Gradient Clipping Becomes a Control Mechanism for Differential Privacy in Deep Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Partohaghighi, Mohammad, Marcia, Roummel, West, Bruce J., Chen, YangQuan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Roughness-Informed Federated Learning
di: Partohaghighi, Mohammad, et al.
Pubblicazione: (2026)

Fractional Order Federated Learning for Battery Electric Vehicle Energy Consumption Modeling
di: Partohaghighi, Mohammad, et al.
Pubblicazione: (2026)

More Optimal Fractional-Order Stochastic Gradient Descent for Non-Convex Optimization Problems
di: Partohaghighi, Mohammad, et al.
Pubblicazione: (2025)

Effective Dimension Aware Fractional-Order Stochastic Gradient Descent for Convex Optimization Problems
di: Partohaghighi, Mohammad, et al.
Pubblicazione: (2025)

Fractional-Order Federated Learning
di: Partohaghighi, Mohammad, et al.
Pubblicazione: (2026)

Statistical Roughness-Informed Machine Unlearning
di: Partohaghighi, Mohammad, et al.
Pubblicazione: (2026)

Deep Learning under Fractional-Order Differential Privacy
di: Partohaghighi, Mohammad, et al.
Pubblicazione: (2026)

SMA-DP: Spectral Memory-Aware Differential Privacy for Deep Learning
di: Partohaghighi, Mohammad, et al.
Pubblicazione: (2026)

Information-Theoretic Generalization Bounds for Stochastic Gradient Descent with Predictable Virtual Noise
di: Partohaghighi, Mohammad
Pubblicazione: (2026)

Symmetric Rank-One Quasi-Newton Methods for Deep Learning Using Cubic Regularization
di: Ranganath, Aditya, et al.
Pubblicazione: (2025)

Nonparametric Variational Differential Privacy via Embedding Parameter Clipping
di: Zein, Dina El, et al.
Pubblicazione: (2026)

To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions
di: Marshall, Noah, et al.
Pubblicazione: (2024)

Adaptive Gradient Clipping for Robust Federated Learning
di: Allouah, Youssef, et al.
Pubblicazione: (2024)

When Differential Privacy Meets Wireless Federated Learning: An Improved Analysis for Privacy and Convergence
di: Yaoling, Chen, et al.
Pubblicazione: (2026)

Double Momentum and Error Feedback for Clipping with Fast Rates and Differential Privacy
di: Islamov, Rustem, et al.
Pubblicazione: (2025)

Enabling Differentially Private Federated Learning for Speech Recognition: Benchmarks, Adaptive Optimizers and Gradient Clipping
di: Pelikan, Martin, et al.
Pubblicazione: (2023)

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks
di: Zhang, Huiqi, et al.
Pubblicazione: (2025)

Can Entry-Wise Clipping Give Spectral Control of Stochastic Gradients?
di: Song, Zitao, et al.
Pubblicazione: (2026)

Regularized Gradient Clipping Provably Trains Wide and Deep Neural Networks
di: Tucat, Matteo, et al.
Pubblicazione: (2024)

Gradient Shaping Beyond Clipping: A Functional Perspective on Update Magnitude Control
di: You, Haochen, et al.
Pubblicazione: (2025)

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

Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping
di: Şimşekli, Umut, et al.
Pubblicazione: (2024)

Weight Clipping for Deep Continual and Reinforcement Learning
di: Elsayed, Mohamed, et al.
Pubblicazione: (2024)

Robust Stochastic Optimization via Gradient Quantile Clipping
di: Merad, Ibrahim, et al.
Pubblicazione: (2023)

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

Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level
di: Khah, Saleh Vatan, et al.
Pubblicazione: (2025)

ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs
di: Zhang, Bonan, et al.
Pubblicazione: (2025)

Negative Binomial Matrix Completion
di: Lu, Yu, et al.
Pubblicazione: (2024)

Skellam Mixture Mechanism: a Novel Approach to Federated Learning with Differential Privacy
di: Bao, Ergute, et al.
Pubblicazione: (2022)

DPDR: Gradient Decomposition and Reconstruction for Differentially Private Deep Learning
di: Liu, Yixuan, et al.
Pubblicazione: (2024)

On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box
di: Cai, Yi, et al.
Pubblicazione: (2023)

From Gradient Clipping to Normalization for Heavy Tailed SGD
di: Hübler, Florian, et al.
Pubblicazione: (2024)

Parameter-free Clipped Gradient Descent Meets Polyak
di: Takezawa, Yuki, et al.
Pubblicazione: (2024)

The Power of Bias: Optimizing Client Selection in Federated Learning with Heterogeneous Differential Privacy
di: Ma, Jiating, et al.
Pubblicazione: (2024)

Adaptive Clipping for Privacy-Preserving Few-Shot Learning: Enhancing Generalization with Limited Data
di: Ranaweera, Kanishka, et al.
Pubblicazione: (2025)

The Fast Mixing Mechanism for Differential Privacy
di: Lev, Omri, et al.
Pubblicazione: (2026)

Near-Optimal Reinforcement Learning with Shuffle Differential Privacy
di: Bai, Shaojie, et al.
Pubblicazione: (2024)

Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy
di: Koloskova, Anastasia, et al.
Pubblicazione: (2023)

Forward Learning with Differential Privacy
di: Feng, Mingqian, et al.
Pubblicazione: (2025)

Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey
di: Demelius, Lea, et al.
Pubblicazione: (2023)