On the Validation of Gibbs Algorithms: Training Datasets, Test Datasets and their Aggregation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

On the Validation of Gibbs Algorithms: Training Datasets, Test Datasets and their Aggregation

Résumé

The dependence on training data of the Gibbs algorithm (GA) is analytically characterized. By adopting the expected empirical risk as the performance metric, the sensitivity of the GA is obtained in closed-form. In this case, sensitivity is the performance difference with respect to an arbitrary alternative algorithm. This description enables the development of explicit expressions involving the training errors and test errors of GAs trained with different datasets. Using these tools, dataset aggregation is studied and different figures of merit to evaluate the generalization capabilities of GAs are introduced. For particular sizes of such datasets and parameters of the GAs, a connection between Jeffrey's divergence, training and test errors is established.
Fichier principal
Vignette du fichier
V2-HAL-ISIT2023.pdf (241.42 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04096054 , version 1 (12-05-2023)
hal-04096054 , version 2 (14-05-2023)
hal-04096054 , version 3 (19-06-2023)

Identifiants

  • HAL Id : hal-04096054 , version 2

Citer

Samir M. Perlaza, Iñaki Esnaola, Gaetan Bisson, H Vincent Poor. On the Validation of Gibbs Algorithms: Training Datasets, Test Datasets and their Aggregation. IEEE International Symposium on Information Theory (ISIT 2023), Jun 2023, Taipei, Taiwan. ⟨hal-04096054v2⟩
98 Consultations
82 Téléchargements

Partager

Gmail Facebook X LinkedIn More