Summary of On the Performance Analysis Of Momentum Method: a Frequency Domain Perspective, by Xianliang Li et al.
On the Performance Analysis of Momentum Method: A Frequency Domain Perspective
by Xianliang Li, Jun Luo, Zhiwei Zheng, Hanxiao Wang, Li Luo, Lingkun Wen, Linlong Wu, Sheng Xu
First submitted to arxiv on: 29 Nov 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 presents a frequency domain analysis framework for understanding the role of momentum in stochastic gradient methods, specifically neural network training. The authors reveal that high-frequency gradient components are undesired in the late stages of training and propose Frequency Stochastic Gradient Descent with Momentum (FSGDM), a heuristic optimizer that dynamically adjusts the momentum filtering characteristic. Experimental results demonstrate FSGDM’s superiority over conventional momentum optimizers. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us understand how to train neural networks better. It shows that some parts of the data are more important than others and proposes a new way to update those parts during training. The authors tested their new method and found it works better than other methods people use today. |
Keywords
» Artificial intelligence » Neural network » Stochastic gradient descent
