Summary of Probabilistic Guarantees Of Stochastic Recursive Gradient in Non-convex Finite Sum Problems, by Yanjie Zhong et al.
Probabilistic Guarantees of Stochastic Recursive Gradient in Non-Convex Finite Sum Problems
by Yanjie Zhong, Jiaqi Li, Soumendra Lahiri
First submitted to arxiv on: 29 Jan 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Machine Learning (cs.LG); Optimization and Control (math.OC); Statistics Theory (math.ST)
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 introduces a novel dimension-free bound for the summation norm of a martingale difference sequence, which enables high-probability bounds for the gradient norm estimator in the Prob-SARAH algorithm. This modified version of SARAH achieves optimal computational complexity and matches the best in-expectation result up to logarithmic factors. Empirical experiments demonstrate the superior probabilistic performance of Prob-SARAH on real datasets compared to other popular algorithms. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper develops a new way to calculate the probability that an algorithm will work well, which is important for machine learning. The researchers create a new version of an existing algorithm called SARAH, which works better than previous versions. They also test this new algorithm on real-world data and show it performs better than other algorithms. |
