Copertina

AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Huiqi, Xie, Fang
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Statistics Theory
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

Provable Generalization Bounds for Deep Neural Networks with Momentum-Adaptive Gradient Dropout
di: Safder, Adeel
Pubblicazione: (2025)

Learning with Differentially Private (Sliced) Wasserstein Gradients
di: Rodríguez-Vítores, David, et al.
Pubblicazione: (2025)

Statistical Guarantees for Approximate Stationary Points of Shallow Neural Networks
di: Taheri, Mahsa, et al.
Pubblicazione: (2022)

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

Differentially Private Two-Stage Gradient Descent for Instrumental Variable Regression
di: Liang, Haodong, et al.
Pubblicazione: (2025)

Factor Augmented High-Dimensional SGD
di: Li, Shubo, et al.
Pubblicazione: (2026)

Contraction of Locally Differentially Private Mechanisms
di: Asoodeh, Shahab, et al.
Pubblicazione: (2022)

Gaussian Differential Private Bootstrap by Subsampling
di: Dette, Holger, et al.
Pubblicazione: (2025)

Convex SGD: Generalization Without Early Stopping
di: Hendrickx, Julien, et al.
Pubblicazione: (2024)

An Algorithm for Streaming Differentially Private Data
di: Kumar, Girish, et al.
Pubblicazione: (2024)

High-dimensional Limit of SGD for Diagonal Linear Networks
di: Malaxechebarría, Begoña García, et al.
Pubblicazione: (2026)

Differentially Private Model-X Knockoffs via Johnson-Lindenstrauss Transform
di: Tao, Yuxuan, et al.
Pubblicazione: (2025)

Differentially Private Manifold Denoising
di: Wu, Jiaqi, et al.
Pubblicazione: (2026)

On Differentially Private U Statistics
di: Chaudhuri, Kamalika, et al.
Pubblicazione: (2024)

Online Detection of Changes in Moment-Based Projections: When to Retrain Deep Learners or Update Portfolios?
di: Steland, Ansgar
Pubblicazione: (2023)

Smoothed SGD for quantiles: Bahadur representation and Gaussian approximation
di: Chen, Likai, et al.
Pubblicazione: (2025)

SGD with Dependent Data: Optimal Estimation, Regret, and Inference
di: Shen, Yinan, et al.
Pubblicazione: (2026)

AdaTrans: Feature-wise and Sample-wise Adaptive Transfer Learning for High-dimensional Regression
di: He, Zelin, et al.
Pubblicazione: (2024)

High-Dimensional Asymptotics of Differentially Private PCA
di: Yun, Youngjoo, et al.
Pubblicazione: (2025)

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

Optimal Differentially Private Ranking from Pairwise Comparisons
di: Cai, T. Tony, et al.
Pubblicazione: (2025)

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

General Lower Bounds for Differentially Private Federated Learning with Arbitrary Public-Transcript Interactions
di: Li, Yicheng
Pubblicazione: (2026)

Differentially Private Two-Stage Empirical Risk Minimization with Applications to Individualized Treatment Rule
di: Lee, Joowon, et al.
Pubblicazione: (2026)

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

Inference for Deep Neural Network Estimators in Generalized Nonparametric Models
di: Meng, Xuran, et al.
Pubblicazione: (2025)

Exploring the Complexity of Deep Neural Networks through Functional Equivalence
di: Shen, Guohao
Pubblicazione: (2023)

Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data
di: Frei, Spencer, et al.
Pubblicazione: (2022)

Optimal Differentially Private PCA and Estimation for Spiked Covariance Matrices
di: Cai, T. Tony, et al.
Pubblicazione: (2024)

A Piecewise Lyapunov Analysis of Sub-quadratic SGD: Applications to Robust and Quantile Regression
di: Zhang, Yixuan, et al.
Pubblicazione: (2025)

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

Differentially Private Synthetic High-dimensional Tabular Stream
di: Kumar, Girish, et al.
Pubblicazione: (2024)

Fixed-Budget Differentially Private Best Arm Identification
di: Chen, Zhirui, et al.
Pubblicazione: (2024)

Pointwise Generalization in Deep Neural Networks
di: Li, Shaojie, et al.
Pubblicazione: (2026)

Differentially Private Federated Learning: Servers Trustworthiness, Estimation, and Statistical Inference
di: Zhang, Zhe, et al.
Pubblicazione: (2024)

Minimax and Adaptive Covariance Matrix Estimation under Differential Privacy
di: Cai, T. Tony, et al.
Pubblicazione: (2026)

Sharp Generalization for Nonparametric Regression in Interpolation Space by Over-Parameterized Neural Networks Trained with Preconditioned Gradient Descent and Early Stopping
di: Yang, Yingzhen, et al.
Pubblicazione: (2024)

Gradient Descent with Projection Finds Over-Parameterized Neural Networks for Learning Low-Degree Polynomials with Nearly Minimax Optimal Rate
di: Yang, Yingzhen, et al.
Pubblicazione: (2026)