Computational Advantages of Multi-Grade Deep Learning: Convergence Analysis and Performance Insights
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918105419087872 |
|---|---|
| author | Fang, Ronglong Xu, Yuesheng |
| author_facet | Fang, Ronglong Xu, Yuesheng |
| contents | Multi-grade deep learning (MGDL) has been shown to significantly outperform the standard single-grade deep learning (SGDL) across various applications. This work aims to investigate the computational advantages of MGDL focusing on its performance in image regression, denoising, and deblurring tasks, and comparing it to SGDL. We establish convergence results for the gradient descent (GD) method applied to these models and provide mathematical insights into MGDL's improved performance. In particular, we demonstrate that MGDL is more robust to the choice of learning rate under GD than SGDL. Furthermore, we analyze the eigenvalue distributions of the Jacobian matrices associated with the iterative schemes arising from the GD iterations, offering an explanation for MGDL's enhanced training stability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_20351 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Computational Advantages of Multi-Grade Deep Learning: Convergence Analysis and Performance Insights Fang, Ronglong Xu, Yuesheng Machine Learning Numerical Analysis Multi-grade deep learning (MGDL) has been shown to significantly outperform the standard single-grade deep learning (SGDL) across various applications. This work aims to investigate the computational advantages of MGDL focusing on its performance in image regression, denoising, and deblurring tasks, and comparing it to SGDL. We establish convergence results for the gradient descent (GD) method applied to these models and provide mathematical insights into MGDL's improved performance. In particular, we demonstrate that MGDL is more robust to the choice of learning rate under GD than SGDL. Furthermore, we analyze the eigenvalue distributions of the Jacobian matrices associated with the iterative schemes arising from the GD iterations, offering an explanation for MGDL's enhanced training stability. |
| title | Computational Advantages of Multi-Grade Deep Learning: Convergence Analysis and Performance Insights |
| topic | Machine Learning Numerical Analysis |
| url | https://arxiv.org/abs/2507.20351 |