Sample-based Federated Learning via Mini-batch SSCA
Not on the map. Why?
Abstract (arXiv)
In this paper, we investigate unconstrained and constrained sample-based federated optimization, respectively. For each problem, we propose a privacy preserving algorithm using stochastic successive convex approximation (SSCA) techniques, and show that it can converge to a Karush-Kuhn-Tucker (KKT) point. To the best of our knowledge, SSCA has not been used for solving federated optimization, and federated optimization with nonconvex constraints has not been investigated. Next, we customize the two proposed SSCA-based algorithms to two application examples, and provide closed-form solutions for the respective approximate convex problems at each iteration of SSCA. Finally, numerical experiments demonstrate inherent advantages of the proposed algorithms in terms of convergence speed, communication cost and model specification.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 6 of its 13 references that are in the map. First posted on arXiv 17 Mar 2021.
Builds on
6 of 13 references.
References · 6
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2019Federated Machine Learning: Concept and Applicationscited by 409
- 2018Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learningcited by 277
- 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 174
- 2019Scheduling Policies for Federated Learning in Wireless Networkscited by 131
- 2017Stochastic Training of Neural Networks via Successive Convex Approximationscited by 2
Built on by
Citing papers per year: 2021: 2.
2 papers.