mlsanityData to 7 Oct 2026

Locally Differentially Private Online Federated Learning With Correlated Noise

arXiv 2411.18752 ↗First posted 27 Nov 2024cs.LG cs.DC stat.MLcited by 6

Not on the map. Why?

Abstract (arXiv)

We introduce a locally differentially private (LDP) algorithm for online federated learning that employs temporally correlated noise to improve utility while preserving privacy. To address challenges posed by the correlated noise and local updates with streaming non-IID data, we develop a perturbed iterate analysis that controls the impact of the noise on the utility. Moreover, we demonstrate how the drift errors from local updates can be effectively managed for several classes of nonconvex loss functions. Subject to an (ε,δ)-LDP budget, we establish a dynamic regret bound that quantifies the impact of key parameters and the intensity of changes in the dynamic environment on the learning performance. Numerical experiments confirm the efficacy of the proposed algorithm.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 25 of its 45 references that are in the map. First posted on arXiv 27 Nov 2024.

Builds on

25 of 45 references.

References · 25

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2016Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Conditioncited by 526
  5. 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 339
  6. 2021Practical and Private (Deep) Learning without Sampling or Shufflingcited by 169
  7. 2022Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streamscited by 59
  8. 2020Wireless Federated Learning with Local Differential Privacycited by 50
  9. 2023(Amplified) Banded Matrix Factorization: A unified approach to private trainingcited by 49
  10. 2016Improved Dynamic Regret for Non-degenerate Functionscited by 46
  11. 2016Calculus of the exponent of Kurdyka-Lojasiewicz inequality and its applications to linear convergence of first-order methodscited by 35
  12. 2021The Price of Differential Privacy under Continual Observationcited by 32
13 more
  1. 2019Online Non-Convex Learning: Following the Perturbed Leader is Optimalcited by 31
  2. 2022Almost Tight Error Bounds on Differentially Private Continual Countingcited by 25
  3. 2013Gradient methods for convex minimization: better rates under weaker conditionscited by 21
  4. 2015A Unified Approach to Error Bounds for Structured Convex Optimization Problemscited by 21
  5. 2023Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacycited by 18
  6. 2015Differentially Private Distributed Online Learningcited by 13
  7. 2023On the Tradeoff between Privacy Preservation and Byzantine-Robustness in Decentralized Learningcited by 8
  8. 2021Improving Dynamic Regret in Distributed Online Mirror Descent Using Primal and Dual Informationcited by 7
  9. 2023A Communication-Efficient Adaptive Algorithm for Federated Learning under Cumulative Regretcited by 7
  10. 2023Linear Speedup of Incremental Aggregated Gradient Methods on Streaming Datacited by 5
  11. 2022Distributed Online Private Learning of Convex Nondecomposable Objectivescited by 4
  12. 2022Distributed Online Non-convex Optimization with Composite Regretcited by 2
  13. 2022Differential Private Discrete Noise Adding Mechanism: Conditions, Properties and Optimizationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 1.

6 papers.

  1. 2025Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGDcited by 7
  2. 2025FedCanon: Non-Convex Composite Federated Learning with Efficient Proximal Operation on Heterogeneous Datacited by 4
  3. 2025Learning Rate Scheduling with Matrix Factorization for Private Trainingcited by 2
  4. 2025Generalization Error Analysis for Attack-Free and Byzantine-Resilient Decentralized Learning with Data Heterogeneitycited by 1
  5. 2025Cocoon: A System Architecture for Differentially Private Training with Correlated Noisescited by 1
  6. 2026Tackling Privacy Heterogeneity in Differentially Private Federated Learningcited by 0