Summary of Review Of Mathematical Optimization in Federated Learning, by Shusen Yang and Fangyuan Zhao and Zihao Zhou and Liang Shi and Xuebin Ren and Zongben Xu
Review of Mathematical Optimization in Federated Learning
by Shusen Yang, Fangyuan Zhao, Zihao Zhou, Liang Shi, Xuebin Ren, Zongben Xu
First submitted to arxiv on: 2 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Distributed, Parallel, and Cluster Computing (cs.DC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper reviews Federated Learning (FL) optimization research, exploring how it collaboratively optimizes aggregate objective functions over distributed datasets while satisfying privacy and system constraints. Unlike conventional distributed optimization methods, FL faces specific challenges like non-i.i.d. data distributions and differential private noises. The review covers existing FL optimization research, including assumptions, formulations, methods, and theoretical results, as well as potential future directions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this paper, researchers explore how Federated Learning can work together to optimize goals while keeping privacy and meeting system requirements. Unlike other methods, FL has special challenges like different data types and private noise issues. The study looks at previous research on FL optimization, including what it assumes, how it works, and the results. It also discusses what might come next. |
Keywords
* Artificial intelligence * Federated learning * Optimization
