Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.16542 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910673891491840 |
|---|---|
| author | Yao, Jiachen Goswami, Mayank Chen, Chao |
| author_facet | Yao, Jiachen Goswami, Mayank Chen, Chao |
| contents | A prevalent assumption regarding real-world data is that it lies on or close to a low-dimensional manifold. When deploying a neural network on data manifolds, the required size, i.e., the number of neurons of the network, heavily depends on the intricacy of the underlying latent manifold. While significant advancements have been made in understanding the geometric attributes of manifolds, it's essential to recognize that topology, too, is a fundamental characteristic of manifolds. In this study, we investigate network expressive power in terms of the latent data manifold. Integrating both topological and geometric facets of the data manifold, we present a size upper bound of ReLU neural networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_16542 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Theoretical Study of Neural Network Expressive Power via Manifold Topology Yao, Jiachen Goswami, Mayank Chen, Chao Machine Learning A prevalent assumption regarding real-world data is that it lies on or close to a low-dimensional manifold. When deploying a neural network on data manifolds, the required size, i.e., the number of neurons of the network, heavily depends on the intricacy of the underlying latent manifold. While significant advancements have been made in understanding the geometric attributes of manifolds, it's essential to recognize that topology, too, is a fundamental characteristic of manifolds. In this study, we investigate network expressive power in terms of the latent data manifold. Integrating both topological and geometric facets of the data manifold, we present a size upper bound of ReLU neural networks. |
| title | A Theoretical Study of Neural Network Expressive Power via Manifold Topology |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2410.16542 |