The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917842789597184 |
|---|---|
| author | Bastounis, Alexander Gorban, Alexander N. Hansen, Anders C. Higham, Desmond J. Prokhorov, Danil Sutton, Oliver Tyukin, Ivan Y. Zhou, Qinghua |
| author_facet | Bastounis, Alexander Gorban, Alexander N. Hansen, Anders C. Higham, Desmond J. Prokhorov, Danil Sutton, Oliver Tyukin, Ivan Y. Zhou, Qinghua |
| contents | In this work, we assess the theoretical limitations of determining guaranteed stability and accuracy of neural networks in classification tasks. We consider classical distribution-agnostic framework and algorithms minimising empirical risks and potentially subjected to some weights regularisation. We show that there is a large family of tasks for which computing and verifying ideal stable and accurate neural networks in the above settings is extremely challenging, if at all possible, even when such ideal solutions exist within the given class of neural architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_07072 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning Bastounis, Alexander Gorban, Alexander N. Hansen, Anders C. Higham, Desmond J. Prokhorov, Danil Sutton, Oliver Tyukin, Ivan Y. Zhou, Qinghua Machine Learning 68T07, 68T05 In this work, we assess the theoretical limitations of determining guaranteed stability and accuracy of neural networks in classification tasks. We consider classical distribution-agnostic framework and algorithms minimising empirical risks and potentially subjected to some weights regularisation. We show that there is a large family of tasks for which computing and verifying ideal stable and accurate neural networks in the above settings is extremely challenging, if at all possible, even when such ideal solutions exist within the given class of neural architectures. |
| title | The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning |
| topic | Machine Learning 68T07, 68T05 |
| url | https://arxiv.org/abs/2309.07072 |