PAC-Bayesian theory for stochastic LTI systems
Document type :
Communication dans un congrès avec actes
Title :
PAC-Bayesian theory for stochastic LTI systems
Author(s) :
Eringis, Deividas [Auteur]
Aalborg University [Denmark] [AAU]
Leth, John [Auteur]
Aalborg University [Denmark] [AAU]
Tan, Zheng-Hua [Auteur]
Aalborg University [Denmark] [AAU]
Wisniewski, Rafal [Auteur]
Aalborg University [Denmark] [AAU]
Esfahani, Alireza Fakhrizadeh [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Petreczky, Mihaly [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Aalborg University [Denmark] [AAU]
Leth, John [Auteur]
Aalborg University [Denmark] [AAU]
Tan, Zheng-Hua [Auteur]
Aalborg University [Denmark] [AAU]
Wisniewski, Rafal [Auteur]
Aalborg University [Denmark] [AAU]
Esfahani, Alireza Fakhrizadeh [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Petreczky, Mihaly [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Conference title :
IEEE Conference on Decision and Control
City :
Austin
Country :
Etats-Unis d'Amérique
Start date of the conference :
2021-12
Publication date :
2021-12
HAL domain(s) :
Informatique [cs]/Apprentissage [cs.LG]
English abstract : [en]
In this paper we derive a PAC-Bayesian error bound for autonomous stochastic LTI state-space models. The motivation for deriving such error bounds is that they will allow deriving similar error bounds for more general ...
Show more >In this paper we derive a PAC-Bayesian error bound for autonomous stochastic LTI state-space models. The motivation for deriving such error bounds is that they will allow deriving similar error bounds for more general dynamical systems, including recurrent neural networks. In turn, PAC-Bayesian error bounds are known to be useful for analyzing machine learning algorithms and for deriving new ones.Show less >
Show more >In this paper we derive a PAC-Bayesian error bound for autonomous stochastic LTI state-space models. The motivation for deriving such error bounds is that they will allow deriving similar error bounds for more general dynamical systems, including recurrent neural networks. In turn, PAC-Bayesian error bounds are known to be useful for analyzing machine learning algorithms and for deriving new ones.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- https://hal.archives-ouvertes.fr/hal-03331763/document
- Open access
- Access the document
- http://arxiv.org/pdf/2103.12866
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-03331763/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-03331763/document
- Open access
- Access the document
- document
- Open access
- Access the document
- CDC2021Arxive.pdf
- Open access
- Access the document
- 2103.12866
- Open access
- Access the document