Summary of Efficient Language Model Architectures For Differentially Private Federated Learning, by Jae Hun Ro et al.
Efficient Language Model Architectures for Differentially Private Federated Learning
by Jae Hun Ro, Srinadh Bhojanapalli, Zheng Xu, Yanxiang Zhang, Ananda Theertha Suresh
First submitted to arxiv on: 12 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); 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 The paper investigates the possibility of using the standard client optimizer, Stochastic Gradient Descent (SGD), for training neural language models in cross-device federated learning (FL) settings. The authors explore whether language models can be modified to achieve efficient training with SGD optimizers, building upon the observation that adaptive optimizers are preferred in centralized training. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In a nutshell, the paper looks at how to train language models using SGD, a popular optimizer for edge devices, and finds a way to make it work efficiently. This is important because it could help us learn from huge amounts of data without moving it around, which can be helpful when working with many devices. |
Keywords
* Artificial intelligence * Federated learning * Stochastic gradient descent
