paper-with-me

홈 › Papers

Federated Cubic Regularized Newton Learning with Sparsification-amplified Differential Privacy

2024-08-08 · Wei Huo, Changxin Liu, Kemi Ding, Karl Henrik Johansson, Ling Shi

This paper investigates the use of the cubic-regularized Newton method within a federated learning framework while addressing two major concerns that commonly arise in federated learning: privacy leakage and communication bottleneck. We introduce a federated learning algorithm called Differentially Private Federated Cubic Regularized Newton (DP-FCRN). By leveraging second-order techniques, our algorithm achieves lower iteration complexity compared to first-order methods. We also incorporate noise perturbation during local computations to ensure privacy. Furthermore, we employ sparsification in uplink transmission, which not only reduces the communication costs but also amplifies the privacy guarantee. Specifically, this approach reduces the necessary noise intensity without compromising privacy protection. We analyze the convergence properties of our algorithm and establish the privacy guarantee. Finally, we validate the effectiveness of the proposed algorithm through experiments on a benchmark dataset.

📄 PDF Abstract BibTeX arXiv:2408.04315

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Escaping Saddle Points in Distributed Newton's Method with Communication Efficiency and Byzantine Resilience

2021-03-17 · Avishek Ghosh, Raj Kumar Maity, Arya Mazumdar, Kannan Ramchandran

The problem of saddle-point avoidance for non-convex optimization is quite challenging in large scale distributed learning frameworks, such as Federated Learning, especially in the presence of Byzantine workers. The cele…

Federated Learning

A Distributed Cubic-Regularized Newton Method for Smooth Convex Optimization over Networks

2020-07-07 · César A. Uribe, Ali Jadbabaie

We propose a distributed, cubic-regularized Newton method for large-scale convex optimization over networks. The proposed method requires only local computations and communications and is suitable for federated learning …

Federated Learning

Cubic-Regularized Newton for Spectral Constrained Matrix Optimization and its Application to Fairness

2022-09-02 · Casey Garner, Gilad Lerman, Shuzhong Zhang

Matrix functions are utilized to rewrite smooth spectral constrained matrix optimization problems as smooth unconstrained problems over the set of symmetric matrices which are then solved via the cubic-regularized Newton…

Fairness

Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate

2024-01-05 · Ruichen Jiang, Parameswaran Raman, Shoham Sabach, Aryan Mokhtari 외

Second-order optimization methods, such as cubic regularized Newton methods, are known for their rapid convergence rates; nevertheless, they become impractical in high-dimensional problems due to their substantial memory…

Second-order methodssubspace methods

Stochastic Variance-Reduced Cubic Regularized Newton Method

2018-02-13 · ICML 2018 7 · Dongruo Zhou, Pan Xu, Quanquan Gu

We propose a stochastic variance-reduced cubic regularized Newton method for non-convex optimization. At the core of our algorithm is a novel semi-stochastic gradient along with a semi-stochastic Hessian, which are speci…