# Dynamic Privacy Allocation for Locally Differentially Private Federated Learning with Composite Objectives

arXiv: https://arxiv.org/abs/2308.01139 · HTML: https://mlsanity.com/paper/2308.01139/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 2 Aug 2023.

## Builds on (most cited first, 12 of 12)

- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds](https://mlsanity.com/paper/1605.02065/) (2016)
- [ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!](https://mlsanity.com/paper/2202.09357/) (2022)
- [Differentially Private Federated Learning on Heterogeneous Data](https://mlsanity.com/paper/2111.09278/) (2021)
- [Differentially Private Federated Learning with Local Regularization and Sparsification](https://mlsanity.com/paper/2203.03106/) (2022)
- [Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses](https://mlsanity.com/paper/2106.09779/) (2021)
- [A Linearly Convergent Proximal Gradient Algorithm for Decentralized Optimization](https://mlsanity.com/paper/1905.07996/) (2019)
- [FLDP: Flexible strategy for local differential privacy](https://mlsanity.com/paper/2203.14875/) (2022)
- [Private and Accurate Decentralized Optimization via Encrypted and Structured Functional Perturbation](https://mlsanity.com/paper/2209.01756/) (2022)
- [Privacy-preserving Automatic Speaker Diarization](https://mlsanity.com/paper/2210.14995/) (2022)
- [Local Graph-homomorphic Processing for Privatized Distributed Systems](https://mlsanity.com/paper/2210.15414/) (2022)

## Built on by (most cited first, 5 of 5)

- [A survey on secure decentralized optimization and learning](https://mlsanity.com/paper/2408.08628/) (2024)
- [Federated Cubic Regularized Newton Learning with Sparsification-amplified Differential Privacy](https://mlsanity.com/paper/2408.04315/) (2024)
- [PAUSE: Low-Latency and Privacy-Aware Active User Selection for Federated Learning](https://mlsanity.com/paper/2503.13173/) (2025)
- [Local Layer-wise Differential Privacy in Federated Learning](https://mlsanity.com/paper/2601.01737/) (2026)
- [Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregation](https://mlsanity.com/paper/2604.07125/) (2026)

## Abstract (arXiv)

This paper proposes a locally differentially private federated learning algorithm for strongly convex but possibly nonsmooth problems that protects the gradients of each worker against an honest but curious server. The proposed algorithm adds artificial noise to the shared information to ensure privacy and dynamically allocates the time-varying noise variance to minimize an upper bound of the optimization error subject to a predefined privacy budget constraint. This allows for an arbitrarily large but finite number of iterations to achieve both privacy protection and utility up to a neighborhood of the optimal solution, removing the need for tuning the number of iterations. Numerical results show the superiority of the proposed algorithm over state-of-the-art methods.