On the Diminishing Returns of Width for Continual Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917698681700352 |
|---|---|
| author | Guha, Etash Lakshman, Vihan |
| author_facet | Guha, Etash Lakshman, Vihan |
| contents | While deep neural networks have demonstrated groundbreaking performance in various settings, these models often suffer from \emph{catastrophic forgetting} when trained on new tasks in sequence. Several works have empirically demonstrated that increasing the width of a neural network leads to a decrease in catastrophic forgetting but have yet to characterize the exact relationship between width and continual learning. We design one of the first frameworks to analyze Continual Learning Theory and prove that width is directly related to forgetting in Feed-Forward Networks (FFN). Specifically, we demonstrate that increasing network widths to reduce forgetting yields diminishing returns. We empirically verify our claims at widths hitherto unexplored in prior studies where the diminishing returns are clearly observed as predicted by our theory. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_06398 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the Diminishing Returns of Width for Continual Learning Guha, Etash Lakshman, Vihan Machine Learning Artificial Intelligence While deep neural networks have demonstrated groundbreaking performance in various settings, these models often suffer from \emph{catastrophic forgetting} when trained on new tasks in sequence. Several works have empirically demonstrated that increasing the width of a neural network leads to a decrease in catastrophic forgetting but have yet to characterize the exact relationship between width and continual learning. We design one of the first frameworks to analyze Continual Learning Theory and prove that width is directly related to forgetting in Feed-Forward Networks (FFN). Specifically, we demonstrate that increasing network widths to reduce forgetting yields diminishing returns. We empirically verify our claims at widths hitherto unexplored in prior studies where the diminishing returns are clearly observed as predicted by our theory. |
| title | On the Diminishing Returns of Width for Continual Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2403.06398 |