Imagen de Portada

PrivSGP-VR: Differentially Private Variance-Reduced Stochastic Gradient Push with Tight Utility Bounds

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhu, Zehan, Huang, Yan, Wang, Xin, Xu, Jinming
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

DP-CSGP: Differentially Private Stochastic Gradient Push with Compressed Communication
por: Zhu, Zehan, et al.
Publicado: (2025)

Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee
por: Zhu, Zehan, et al.
Publicado: (2025)

ADP-VRSGP: Decentralized Learning with Adaptive Differential Privacy via Variance-Reduced Stochastic Gradient Push
por: Wu, Xiaoming, et al.
Publicado: (2025)

PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning
por: Gong, Chen, et al.
Publicado: (2025)

A Variance-Reduced Stochastic Gradient Tracking Algorithm for Decentralized Optimization with Orthogonality Constraints
por: Wang, Lei, et al.
Publicado: (2022)

PrivATE: Differentially Private Confidence Intervals for Average Treatment Effects
por: Schröder, Maresa, et al.
Publicado: (2025)

Almost Tight Error Bounds on Differentially Private Continual Counting
por: Henzinger, Monika, et al.
Publicado: (2022)

Statistical Inference for Differentially Private Stochastic Gradient Descent
por: Xia, Xintao, et al.
Publicado: (2025)

Tight Generalization Error Bounds for Stochastic Gradient Descent in Non-convex Learning
por: Xiong, Wenjun, et al.
Publicado: (2025)

Robust Fully-Asynchronous Methods for Distributed Training over General Architecture
por: Zhu, Zehan, et al.
Publicado: (2023)

Stochastic Gradient Langevin Dynamics with Variance Reduction
por: Huang, Zhishen, et al.
Publicado: (2021)

PrivEraserVerify: Efficient, Private, and Verifiable Federated Unlearning
por: Goswami, Parthaw, et al.
Publicado: (2026)

Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent
por: Yu, Da, et al.
Publicado: (2022)

On the Stochastic (Variance-Reduced) Proximal Gradient Method for Regularized Expected Reward Optimization
por: Liang, Ling, et al.
Publicado: (2024)

An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses
por: Liang, Hao, et al.
Publicado: (2025)

Differentially Private Policy Gradient
por: Rio, Alexandre, et al.
Publicado: (2025)

Almost Sure Convergence Analysis of Differentially Private Stochastic Gradient Methods
por: Mukherjee, Amartya, et al.
Publicado: (2025)

PrivDFS: Private Inference via Distributed Feature Sharing against Data Reconstruction Attacks
por: Liu, Zihan, et al.
Publicado: (2025)

PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining
por: Li, Kecen, et al.
Publicado: (2023)

Tight Differentially Private PCA via Matrix Coherence
por: d'Orsi, Tommaso, et al.
Publicado: (2025)

Limit Theorems for Stochastic Gradient Descent with Infinite Variance
por: Blanchet, Jose, et al.
Publicado: (2024)

Unified High-Probability Analysis of Stochastic Variance-Reduced Estimation
por: Luo, Zhankun, et al.
Publicado: (2026)

Closing the Gap Between SGP4 and High-Precision Propagation via Differentiable Programming
por: Acciarini, Giacomo, et al.
Publicado: (2024)

Generalization Bounds of Stochastic Gradient Descent in Homogeneous Neural Networks
por: Ma, Wenquan, et al.
Publicado: (2026)

Beyond Ordinary Lipschitz Constraints: Differentially Private Stochastic Optimization with Tsybakov Noise Condition
por: Xu, Difei, et al.
Publicado: (2025)

Finding Differentially Private Second Order Stationary Points in Stochastic Minimax Optimization
por: Xu, Difei, et al.
Publicado: (2026)

Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
por: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Publicado: (2024)

Differentially Private Optimization with Sparse Gradients
por: Ghazi, Badih, et al.
Publicado: (2024)

Improving the Variance of Differentially Private Randomized Experiments through Clustering
por: Javanmard, Adel, et al.
Publicado: (2023)

Tight Bounds for Logistic Regression with Large Stepsize Gradient Descent in Low Dimension
por: Crawshaw, Michael, et al.
Publicado: (2026)

Improving the Utility of Differentially Private Clustering through Dynamical Processing
por: Byun, Junyoung, et al.
Publicado: (2023)

Variance-Aware Regret Bounds for Stochastic Contextual Dueling Bandits
por: Di, Qiwei, et al.
Publicado: (2023)

Solving Stochastic Variational Inequalities without the Bounded Variance Assumption
por: Alacaoglu, Ahmet, et al.
Publicado: (2026)

Near-Optimal Algorithms for Differentially Private Online Learning in a Stochastic Environment
por: Hu, Bingshan, et al.
Publicado: (2021)

Optimizing Stochastic Gradient Push under Broadcast Communications
por: Nguyen, Tuan, et al.
Publicado: (2026)

Gradient Estimation and Variance Reduction in Stochastic and Deterministic Models
por: Keane, Ronan
Publicado: (2024)

Beyond Bounded Variance: Variance-Reduced Normalized Methods for Nonconvex Optimization under Blum-Gladyshev Noise
por: Upadhyay, Antesh, et al.
Publicado: (2026)

Graphical vs. Deep Generative Models: Measuring the Impact of Differentially Private Mechanisms and Budgets on Utility
por: Ganev, Georgi, et al.
Publicado: (2023)

Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement
por: Birrell, Jeremiah, et al.
Publicado: (2024)

Variance-Reduced $(\varepsilon,δ)-$Unlearning using Forget Set Gradients
por: Van Waerebeke, Martin, et al.
Publicado: (2026)