Summary of Dynamic Decoupling Of Placid Terminal Attractor-based Gradient Descent Algorithm, by Jinwei Zhao (1) et al.
Dynamic Decoupling of Placid Terminal Attractor-based Gradient Descent Algorithm
by Jinwei Zhao, Marco Gori, Alessandro Betti, Stefano Melacci, Hongtao Zhang, Jiedong Liu, Xinhong Hei
First submitted to arxiv on: 10 Sep 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 investigates the dynamics of gradient descent (GD) and stochastic gradient descent (SGD), two widely used optimization techniques in machine learning. The authors analyze the terminal attractor at different stages of the gradient flow, leveraging the terminal sliding mode theory and terminal attractor theory to design four adaptive learning rates. They theoretically investigate the performance of these rates and evaluate their running times on a function approximation problem and an image classification problem. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us understand how our computers learn from data by studying two important tools: gradient descent (GD) and stochastic gradient descent (SGD). The authors looked at how GD works at different stages and used that to create new ways of adjusting the learning rate. They tested these new methods on a few problems, like fitting curves to data and classifying images. |
Keywords
» Artificial intelligence » Gradient descent » Image classification » Machine learning » Optimization » Stochastic gradient descent
