Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2205.14627 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915356283502592 |
|---|---|
| author | Alberti, Giovanni S. Santacesaria, Matteo Sciutto, Silvia |
| author_facet | Alberti, Giovanni S. Santacesaria, Matteo Sciutto, Silvia |
| contents | In this work, we present and study Continuous Generative Neural Networks (CGNNs), namely, generative models in the continuous setting: the output of a CGNN belongs to an infinite-dimensional function space. The architecture is inspired by DCGAN, with one fully connected layer, several convolutional layers and nonlinear activation functions. In the continuous $L^2$ setting, the dimensions of the spaces of each layer are replaced by the scales of a multiresolution analysis of a compactly supported wavelet. We present conditions on the convolutional filters and on the nonlinearity that guarantee that a CGNN is injective. This theory finds applications to inverse problems, and allows for deriving Lipschitz stability estimates for (possibly nonlinear) infinite-dimensional inverse problems with unknowns belonging to the manifold generated by a CGNN. Several numerical simulations, including signal deblurring, illustrate and validate this approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2205_14627 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Continuous Generative Neural Networks: A Wavelet-Based Architecture in Function Spaces Alberti, Giovanni S. Santacesaria, Matteo Sciutto, Silvia Machine Learning In this work, we present and study Continuous Generative Neural Networks (CGNNs), namely, generative models in the continuous setting: the output of a CGNN belongs to an infinite-dimensional function space. The architecture is inspired by DCGAN, with one fully connected layer, several convolutional layers and nonlinear activation functions. In the continuous $L^2$ setting, the dimensions of the spaces of each layer are replaced by the scales of a multiresolution analysis of a compactly supported wavelet. We present conditions on the convolutional filters and on the nonlinearity that guarantee that a CGNN is injective. This theory finds applications to inverse problems, and allows for deriving Lipschitz stability estimates for (possibly nonlinear) infinite-dimensional inverse problems with unknowns belonging to the manifold generated by a CGNN. Several numerical simulations, including signal deblurring, illustrate and validate this approach. |
| title | Continuous Generative Neural Networks: A Wavelet-Based Architecture in Function Spaces |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2205.14627 |