Image de couverture de livre

Smoothed Normalization for Efficient Distributed Private Optimization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shulgin, Egor, Khirirat, Sarit, Richtárik, Peter
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Cryptography and Security Distributed, Parallel, and Cluster Computing Optimization and Control
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Towards a Better Theoretical Understanding of Independent Subnetwork Training
par: Shulgin, Egor, et autres
Publié: (2023)

MAST: Model-Agnostic Sparsified Training
par: Demidovich, Yury, et autres
Publié: (2023)

Residual-Evasive Attacks on ADMM in Distributed Optimization
par: Bruckmeier, Sabrina, et autres
Publié: (2025)

FedADMM-InSa: An Inexact and Self-Adaptive ADMM for Federated Learning
par: Song, Yongcun, et autres
Publié: (2024)

The Privacy Power of Correlated Noise in Decentralized Learning
par: Allouah, Youssef, et autres
Publié: (2024)

Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity
par: Mahran, Ammar, et autres
Publié: (2026)

LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression
par: Condat, Laurent, et autres
Publié: (2024)

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

ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning
par: Maranjyan, Artavazd, et autres
Publié: (2025)

On Biased Compression for Distributed Learning
par: Beznosikov, Aleksandr, et autres
Publié: (2020)

Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction
par: Tovmasyan, Zhirayr, et autres
Publié: (2026)

Ringleader ASGD: The First Asynchronous SGD with Optimal Time Complexity under Data Heterogeneity
par: Maranjyan, Artavazd, et autres
Publié: (2025)

MindFlayer SGD: Efficient Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times
par: Maranjyan, Artavazd, et autres
Publié: (2024)

Seeking Consensus on Subspaces in Federated Principal Component Analysis
par: Wang, Lei, et autres
Publié: (2020)

Correlated Quantization for Faster Nonconvex Distributed Optimization
par: Panferov, Andrei, et autres
Publié: (2024)

Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity
par: Maranjyan, Artavazd, et autres
Publié: (2025)

GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity
par: Maranjyan, Artavazd, et autres
Publié: (2022)

First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions
par: Shulgin, Egor, et autres
Publié: (2025)

Efficient Language Model Architectures for Differentially Private Federated Learning
par: Ro, Jae Hun, et autres
Publié: (2024)

Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method
par: Sadiev, Abdurakhmon, et autres
Publié: (2026)

LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging
par: Maziane, Yassine, et autres
Publié: (2026)

Efficient and Scalable Implementation of Differentially Private Deep Learning without Shortcuts
par: Beltran, Sebastian Rodriguez, et autres
Publié: (2024)

Enhancing Privacy in Decentralized Min-Max Optimization: A Differentially Private Approach
par: Quan, Yueyang, et autres
Publié: (2025)

TernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Data
par: Jin, Richeng, et autres
Publié: (2024)

Differentially Private Clustered Federated Learning
par: Malekmohammadi, Saber, et autres
Publié: (2024)

Differentially-Private Multi-Tier Federated Learning
par: Chen, Evan, et autres
Publié: (2024)

Age Aware Scheduling for Differentially-Private Federated Learning
par: Lin, Kuan-Yu, et autres
Publié: (2024)

Differentially Private Online Federated Learning with Correlated Noise
par: Zhang, Jiaojiao, et autres
Publié: (2024)

DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning
par: Mehmood, Haaris, et autres
Publié: (2026)

Differentially Private Federated Learning With Time-Adaptive Privacy Spending
par: Kiani, Shahrzad, et autres
Publié: (2025)

Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning
par: Malekmohammadi, Saber, et autres
Publié: (2024)

Dropout-Robust Mechanisms for Differentially Private and Fully Decentralized Mean Estimation
par: Sabater, César, et autres
Publié: (2025)

Private Aggregation in Hierarchical Wireless Federated Learning with Partial and Full Collusion
par: Egger, Maximilian, et autres
Publié: (2023)

Prada: Black-Box LLM Adaptation with Private Data on Resource-Constrained Devices
par: Wang, Ziyao, et autres
Publié: (2025)

Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning
par: Egger, Maximilian, et autres
Publié: (2025)

Communication-Efficient and Differentially Private Vertical Federated Learning with Zeroth-Order Optimization
par: Zhang, Jianing, et autres
Publié: (2025)

DP$^2$-FedSAM: Enhancing Differentially Private Federated Learning Through Personalized Sharpness-Aware Minimization
par: Zhang, Zhenxiao, et autres
Publié: (2024)

Private Knowledge Sharing in Distributed Learning: A Survey
par: Supeksala, Yasas, et autres
Publié: (2024)

DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptation
par: Xu, Jie, et autres
Publié: (2024)

Efficient Adaptive Federated Optimization
par: Lee, Su Hyeong, et autres
Publié: (2024)