Scaling Continuous Kernels with Sparse Fourier Domain 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_ | 1866910605139509248 |
|---|---|
| author | Harper, Clayton Wood, Luke Gerstoft, Peter Larson, Eric C. |
| author_facet | Harper, Clayton Wood, Luke Gerstoft, Peter Larson, Eric C. |
| contents | We address three key challenges in learning continuous kernel representations: computational efficiency, parameter efficiency, and spectral bias. Continuous kernels have shown significant potential, but their practical adoption is often limited by high computational and memory demands. Additionally, these methods are prone to spectral bias, which impedes their ability to capture high-frequency details. To overcome these limitations, we propose a novel approach that leverages sparse learning in the Fourier domain. Our method enables the efficient scaling of continuous kernels, drastically reduces computational and memory requirements, and mitigates spectral bias by exploiting the Gibbs phenomenon. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_09875 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Scaling Continuous Kernels with Sparse Fourier Domain Learning Harper, Clayton Wood, Luke Gerstoft, Peter Larson, Eric C. Machine Learning We address three key challenges in learning continuous kernel representations: computational efficiency, parameter efficiency, and spectral bias. Continuous kernels have shown significant potential, but their practical adoption is often limited by high computational and memory demands. Additionally, these methods are prone to spectral bias, which impedes their ability to capture high-frequency details. To overcome these limitations, we propose a novel approach that leverages sparse learning in the Fourier domain. Our method enables the efficient scaling of continuous kernels, drastically reduces computational and memory requirements, and mitigates spectral bias by exploiting the Gibbs phenomenon. |
| title | Scaling Continuous Kernels with Sparse Fourier Domain Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2409.09875 |