Summary of Profl: Performative Robust Optimal Federated Learning, by Xue Zheng et al.
ProFL: Performative Robust Optimal Federated Learning
by Xue Zheng, Tian Xie, Xuwei Tan, Aylin Yener, Xueru Zhang, Ali Payani, Myungjin Lee
First submitted to arxiv on: 23 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Information Theory (cs.IT)
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 proposes Performative Robust Optimal Federated Learning (ProFL), an algorithm that finds performative optimal points in federated learning from noisy and contaminated data. The authors address the shortcomings of existing methods, including Jin et al.’s straightforward extension to federated learning, which only converges to a performative stable point, and Izzo et al.’s and Miller et al.’s algorithms, which require convexity and noiselessness. ProFL overcomes these limitations by presenting convergence analysis under the Polyak-Lojasiewicz condition, applicable to non-convex objectives. Extensive experiments on multiple datasets validate the proposed algorithm’s efficiency. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a new way to learn with computers that are connected together and share information. Right now, when we use these computers to learn from data, they can change how they process that data over time. This can cause problems because the data might not be what it used to be. The researchers looked at ways to fix this problem by creating a new algorithm called ProFL. They tested this algorithm on several different datasets and found that it works well even when the data is noisy or contaminated. |
Keywords
» Artificial intelligence » Federated learning
