Universal Approximation of Operators with Transformers and Neural Integral Operators
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911621642715136 |
|---|---|
| author | Zappala, Emanuele Bagherian, Maryam |
| author_facet | Zappala, Emanuele Bagherian, Maryam |
| contents | We study the universal approximation properties of transformers and neural integral operators for operators in Banach spaces. In particular, we show that the transformer architecture is a universal approximator of integral operators between Hölder spaces. Moreover, we show that a generalized version of neural integral operators, based on the Gavurin integral, are universal approximators of arbitrary operators between Banach spaces. Lastly, we show that a modified version of transformer, which uses Leray-Schauder mappings, is a universal approximator of operators between arbitrary Banach spaces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_00841 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Universal Approximation of Operators with Transformers and Neural Integral Operators Zappala, Emanuele Bagherian, Maryam Machine Learning Numerical Analysis We study the universal approximation properties of transformers and neural integral operators for operators in Banach spaces. In particular, we show that the transformer architecture is a universal approximator of integral operators between Hölder spaces. Moreover, we show that a generalized version of neural integral operators, based on the Gavurin integral, are universal approximators of arbitrary operators between Banach spaces. Lastly, we show that a modified version of transformer, which uses Leray-Schauder mappings, is a universal approximator of operators between arbitrary Banach spaces. |
| title | Universal Approximation of Operators with Transformers and Neural Integral Operators |
| topic | Machine Learning Numerical Analysis |
| url | https://arxiv.org/abs/2409.00841 |