Summary of Budgeted Online Model Selection and Fine-tuning Via Federated Learning, by Pouya M. Ghari et al.
Budgeted Online Model Selection and Fine-Tuning via Federated Learning
by Pouya M. Ghari, Yanning Shen
First submitted to arxiv on: 19 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 proposes an online federated model selection framework for selecting models from a set of candidate models on edge devices with limited memory. The approach involves clients interacting with a server that stores all candidate models, and each client choosing to store a subset of models within its memory constraints. The algorithm also includes collaboration between clients and the server to fine-tune models to adapt to non-stationary environments. Theoretical analysis shows that the proposed algorithm enjoys sub-linear regret with respect to the best model in hindsight, while experiments on real datasets demonstrate its effectiveness. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us choose the right computer program for making predictions when we have many options and limited space. It’s like having a big library of books, but each person only has room for a few books on their bookshelf. The solution involves sharing information between people with lots of storage and those with limited space to help everyone find the best book (model) for the job. |
