Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2405.10054 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911883084169216 |
|---|---|
| author | Racz, Daniel Gonzalez, Martin Petreczky, Mihaly Benczur, Andras Daroczy, Balint |
| author_facet | Racz, Daniel Gonzalez, Martin Petreczky, Mihaly Benczur, Andras Daroczy, Balint |
| contents | One of the main theoretical challenges in learning dynamical systems from data is providing upper bounds on the generalization error, that is, the difference between the expected prediction error and the empirical prediction error measured on some finite sample. In machine learning, a popular class of such bounds are the so-called Probably Approximately Correct (PAC) bounds. In this paper, we derive a PAC bound for stable continuous-time linear parameter-varying (LPV) systems. Our bound depends on the H2 norm of the chosen class of the LPV systems, but does not depend on the time interval for which the signals are considered. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_10054 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A finite-sample generalization bound for stable LPV systems Racz, Daniel Gonzalez, Martin Petreczky, Mihaly Benczur, Andras Daroczy, Balint Machine Learning Systems and Control 68 I.2.0 One of the main theoretical challenges in learning dynamical systems from data is providing upper bounds on the generalization error, that is, the difference between the expected prediction error and the empirical prediction error measured on some finite sample. In machine learning, a popular class of such bounds are the so-called Probably Approximately Correct (PAC) bounds. In this paper, we derive a PAC bound for stable continuous-time linear parameter-varying (LPV) systems. Our bound depends on the H2 norm of the chosen class of the LPV systems, but does not depend on the time interval for which the signals are considered. |
| title | A finite-sample generalization bound for stable LPV systems |
| topic | Machine Learning Systems and Control 68 I.2.0 |
| url | https://arxiv.org/abs/2405.10054 |