Functional Large Deviations for Wide Deep Neural Networks with Gaussian Initialization and Lipschitz Activations
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911399244988416 |
|---|---|
| author | Macci, Claudio Pacchiarotti, Barbara Papagiannouli, Katerina Torrisi, Giovanni Luca Trevisan, Dario |
| author_facet | Macci, Claudio Pacchiarotti, Barbara Papagiannouli, Katerina Torrisi, Giovanni Luca Trevisan, Dario |
| contents | We establish a functional large deviation principle for fully connected multi-layer perceptrons with i.i.d. Gaussian weights (LeCun initialization) and general Lipschitz activation functions, including therefore the popular case of ReLU. The large deviation principle holds for the entire network output process on any compact input set. The proof combines exponential tightness for recursively defined processes, finite-dimensional large deviations, and the Dawson-Gärtner theorem, extending existing results beyond finite input sets and less general activations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_18276 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Functional Large Deviations for Wide Deep Neural Networks with Gaussian Initialization and Lipschitz Activations Macci, Claudio Pacchiarotti, Barbara Papagiannouli, Katerina Torrisi, Giovanni Luca Trevisan, Dario Probability Statistics Theory 60F10, 68T07 We establish a functional large deviation principle for fully connected multi-layer perceptrons with i.i.d. Gaussian weights (LeCun initialization) and general Lipschitz activation functions, including therefore the popular case of ReLU. The large deviation principle holds for the entire network output process on any compact input set. The proof combines exponential tightness for recursively defined processes, finite-dimensional large deviations, and the Dawson-Gärtner theorem, extending existing results beyond finite input sets and less general activations. |
| title | Functional Large Deviations for Wide Deep Neural Networks with Gaussian Initialization and Lipschitz Activations |
| topic | Probability Statistics Theory 60F10, 68T07 |
| url | https://arxiv.org/abs/2601.18276 |