Asymptotic convexity of wide and shallow neural networks
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_ | 1866911138004860928 |
|---|---|
| author | Borkar, Vivek Pandit, Parthe |
| author_facet | Borkar, Vivek Pandit, Parthe |
| contents | For a simple model of shallow and wide neural networks, we show that the epigraph of its input-output map as a function of the network parameters approximates epigraph of a. convex function in a precise sense. This leads to a plausible explanation of their observed good performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_01044 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Asymptotic convexity of wide and shallow neural networks Borkar, Vivek Pandit, Parthe Machine Learning Probability 68T07 For a simple model of shallow and wide neural networks, we show that the epigraph of its input-output map as a function of the network parameters approximates epigraph of a. convex function in a precise sense. This leads to a plausible explanation of their observed good performance. |
| title | Asymptotic convexity of wide and shallow neural networks |
| topic | Machine Learning Probability 68T07 |
| url | https://arxiv.org/abs/2507.01044 |