Cours/Séminaire
Notice
Crédits
Samir M. Perlaza (Intervention)
Conditions d'utilisation
Droit commun de la propriété intellectuelle
Citer cette ressource :
Samir M. Perlaza. FOUNDS. FOUNDS Seminar Series Talk 13 - Generalization Error of Machine Learning Algorithms. [Vidéo]. Canal-U. https://www.canal-u.tv/157445. (Consultée le 9 novembre 2026)
FOUNDS
FOUNDS
S'abonner
Contacter

FOUNDS Seminar Series Talk 13 - Generalization Error of Machine Learning Algorithms

Mise en ligne : 25 octobre 2024
  • document 1 document 2 document 3
  • niveau 1 niveau 2 niveau 3
Descriptif

In this talk, the method of gaps, a technique for deriving closed-form expressions for the generalization error of machine learning algorithms in terms of information measures is introduced. The method relies on two central observations: (a) The generalization error is an average of the variation of the expected empirical risk with respect to changes on the probability measure (used for expectation); and (b) these variations, also referred to as gaps, exhibit closed-form expressions in terms of information measures. The expectation of the empirical risk can be either with respect to a measure on the models (with a fixed dataset) or with respect to a measure on the datasets (with a fixed model), which results in two variants of the method of gaps. The first variant, which focuses on the gaps of the expected empirical risk with respect to a measure on the models, appears to be the most general, as no assumptions are made on the distribution of the datasets. The second variant develops under the assumption that datasets are made of independent and identically distributed data points. All existing exact expressions for the generalization error of machine learning algorithms can be obtained with the proposed method. Also, this method allows obtaining numerous new exact expressions, which improves the understanding of the generalization error; establish connections with other areas in statistics, e.g., hypothesis testing; and potentially, might guide algorithm designs.

Intervention / Responsable scientifique
Portrait Perlaza
Perlaza
Samir M.
Titulaire d'un doctorat en électronique et communications de Télécom ParisTech (2011)

Chargé de Recherche, Centre Inria d'Université Côte d'Azur, Sophia Antipolis, France. Chercheur Associé au Laboratoire de Géométrie Algébrique et Applications à la Théorie de l’Information (GAATI), Université de la Polynésie Française, Faaa, French Polynesia. Visiting Research Collaborator, Department of Electrical and Computer Engineering, Princeton University, Princeton, New Jersey, USA.

Directeur et membre du jury d'une thèse en Informatique à Université Côte d'Azur en 2026
Thème
Disciplines :
Documentation

Sur le même thème