Buchumschlag

Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Zhu, Zehan, Huang, Yan, Wang, Xin, Ji, Shouling, Xu, Jinming
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Machine Learning Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

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

PrivSGP-VR: Differentially Private Variance-Reduced Stochastic Gradient Push with Tight Utility Bounds
von: Zhu, Zehan, et al.
Veröffentlicht: (2024)

Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off
von: Li, Yuecheng, et al.
Veröffentlicht: (2024)

Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guarantees
von: Tao, Lue, et al.
Veröffentlicht: (2023)

Generalizing Differentially Private Decentralized Deep Learning with Multi-Agent Consensus
von: Bayrooti, Jasmine, et al.
Veröffentlicht: (2023)

Multi-Objective Optimization for Privacy-Utility Balance in Differentially Private Federated Learning
von: Ranaweera, Kanishka, et al.
Veröffentlicht: (2025)

Provable Differentially Private Computation of the Cross-Attention Mechanism
von: Ke, Yekun, et al.
Veröffentlicht: (2024)

Model-agnostic Selective Labeling with Provable Statistical Guarantees
von: Huang, Huipeng, et al.
Veröffentlicht: (2025)

On the Provable Performance Guarantee of Efficient Reasoning Models
von: Zeng, Hao, et al.
Veröffentlicht: (2025)

Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
von: Choquette-Choo, Christopher A., et al.
Veröffentlicht: (2023)

Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guarantee
von: Gao, Mengtong, et al.
Veröffentlicht: (2024)

Provable Effects of Data Replay in Continual Learning: A Feature Learning Perspective
von: Ding, Meng, et al.
Veröffentlicht: (2026)

On the Fairness of Privacy Protection: Measuring and Mitigating the Disparity of Group Privacy Risks for Differentially Private Machine Learning
von: Yang, Zhi, et al.
Veröffentlicht: (2025)

DynMuon: A Dynamic Spectral Shaping View of Muon
von: Wu, Fangzhou, et al.
Veröffentlicht: (2026)

From Complex Dynamics to DynFormer: Rethinking Transformers for PDEs
von: Lai, Pengyu, et al.
Veröffentlicht: (2026)

Enumerating Safe Regions in Deep Neural Networks with Provable Probabilistic Guarantees
von: Marzari, Luca, et al.
Veröffentlicht: (2023)

COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees
von: Wang, Zhiyuan, et al.
Veröffentlicht: (2025)

What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systems
von: Bensalem, Saddek, et al.
Veröffentlicht: (2023)

Implicit Hypergraph Neural Networks: A Stable Framework for Higher-Order Relational Learning with Provable Guarantees
von: Li, Xiaoyu, et al.
Veröffentlicht: (2025)

Federated Learning with Differential Privacy: An Utility-Enhanced Approach
von: Ranaweera, Kanishka, et al.
Veröffentlicht: (2025)

Provable Privacy Advantages of Decentralized Federated Learning via Distributed Optimization
von: Yu, Wenrui, et al.
Veröffentlicht: (2024)

On Mitigating the Utility-Loss in Differentially Private Learning: A new Perspective by a Geometrically Inspired Kernel Approach
von: Kumar, Mohit, et al.
Veröffentlicht: (2023)

Provable Privacy with Non-Private Pre-Processing
von: Hu, Yaxi, et al.
Veröffentlicht: (2024)

Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning
von: Banerjee, Arko, et al.
Veröffentlicht: (2024)

Towards Differentially Private Reinforcement Learning with General Function Approximation
von: He, Yi, et al.
Veröffentlicht: (2026)

Provable Scaling Laws of Feature Emergence from Learning Dynamics of Grokking
von: Tian, Yuandong
Veröffentlicht: (2025)

The Path Not Taken: RLVR Provably Learns Off the Principals
von: Zhu, Hanqing, et al.
Veröffentlicht: (2025)

Overcoming Data and Model Heterogeneities in Decentralized Federated Learning via Synthetic Anchors
von: Huang, Chun-Yin, et al.
Veröffentlicht: (2024)

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

Statistical Limits and Efficient Algorithms for Differentially Private Federated Learning
von: Auddy, Arnab, et al.
Veröffentlicht: (2026)

Differentially Private Federated Clustering with Random Rebalancing
von: Yang, Xiyuan, et al.
Veröffentlicht: (2025)

On the Sample Complexity of Differentially Private Policy Optimization
von: He, Yi, et al.
Veröffentlicht: (2025)

Triadic-OCD: Asynchronous Online Change Detection with Provable Robustness, Optimality, and Convergence
von: Huang, Yancheng, et al.
Veröffentlicht: (2024)

PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees
von: Xie, Chulin, et al.
Veröffentlicht: (2023)

Gaussian DP for Reporting Differential Privacy Guarantees in Machine Learning
von: Gomez, Juan Felipe, et al.
Veröffentlicht: (2025)

Revisiting Meta-Learning with Noisy Labels: Reweighting Dynamics and Theoretical Guarantees
von: Zhang, Yiming, et al.
Veröffentlicht: (2025)

Learning Dynamic Graph Embeddings with Neural Controlled Differential Equations
von: Qin, Tiexin, et al.
Veröffentlicht: (2023)

DynScaling: Efficient Verifier-free Inference Scaling via Dynamic and Integrated Sampling
von: Wang, Fei, et al.
Veröffentlicht: (2025)

CONTINA: Confidence Interval for Traffic Demand Prediction with Coverage Guarantee
von: Yang, Chao, et al.
Veröffentlicht: (2025)

Differentially Private Deep Model-Based Reinforcement Learning
von: Rio, Alexandre, et al.
Veröffentlicht: (2024)