Titre :

Controlling Confusion via Generalisation Bounds

Auteur(s) :

Adams, Reuben [Auteur]
Department of Computer science [University College of London] [UCL-CS]
The Inria London Programme [Inria-London]
Shawe-Taylor, John [Auteur]
Department of Computer science [University College of London] [UCL-CS]
Guedj, Benjamin [Auteur]
Department of Computer science [University College of London] [UCL-CS]
The Alan Turing Institute
The Inria London Programme [Inria-London]
MOdel for Data Analysis and Learning [MODAL]

Mot(s)-clé(s) en anglais :

Statistical Learning Theory
PAC-Bayes theory
Classification
Generalisation Bounds

Discipline(s) HAL :

Statistiques [stat]/Machine Learning [stat.ML]
Informatique [cs]/Apprentissage [cs.LG]
Statistiques [stat]/Théorie [stat.TH]

Résumé en anglais : [en]

We establish new generalisation bounds for multiclass classification by abstracting to a more general setting of discretised error types. Extending the PAC-Bayes theory, we are hence able to provide fine-grained bounds on ...
Lire la suite >We establish new generalisation bounds for multiclass classification by abstracting to a more general setting of discretised error types. Extending the PAC-Bayes theory, we are hence able to provide fine-grained bounds on performance for multiclass classification, as well as applications to other learning problems including discretisation of regression losses. Tractable training objectives are derived from the bounds. The bounds are uniform over all weightings of the discretised error types and thus can be used to bound weightings not foreseen at training, including the full confusion matrix in the multiclass classification case.Lire moins >

Langue :

Anglais

Commentaire :

31 pages

Collections :

• Laboratoire Paul Painlevé - UMR 8524

Source :

Harvested from HAL