Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.19033 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909441345978368 |
|---|---|
| author | Xu, Shuntuo Yu, Zhou |
| author_facet | Xu, Shuntuo Yu, Zhou |
| contents | This paper investigates the connection between neural networks and sufficient dimension reduction (SDR), demonstrating that neural networks inherently perform SDR in regression tasks under appropriate rank regularizations. Specifically, the weights in the first layer span the central mean subspace. We establish the statistical consistency of the neural network-based estimator for the central mean subspace, underscoring the suitability of neural networks in addressing SDR-related challenges. Numerical experiments further validate our theoretical findings, and highlight the underlying capability of neural networks to facilitate SDR compared to the existing methods. Additionally, we discuss an extension to unravel the central subspace, broadening the scope of our investigation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_19033 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Neural Networks Perform Sufficient Dimension Reduction Xu, Shuntuo Yu, Zhou Machine Learning This paper investigates the connection between neural networks and sufficient dimension reduction (SDR), demonstrating that neural networks inherently perform SDR in regression tasks under appropriate rank regularizations. Specifically, the weights in the first layer span the central mean subspace. We establish the statistical consistency of the neural network-based estimator for the central mean subspace, underscoring the suitability of neural networks in addressing SDR-related challenges. Numerical experiments further validate our theoretical findings, and highlight the underlying capability of neural networks to facilitate SDR compared to the existing methods. Additionally, we discuss an extension to unravel the central subspace, broadening the scope of our investigation. |
| title | Neural Networks Perform Sufficient Dimension Reduction |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2412.19033 |