Titre :

Learning from Networked Examples

Auteur(s) :

Wang, Yuyi [Auteur]
Nanjing Institute of Geology and Palaeontology [NIGPAS-CAS]
Guo, Zheng-Chu [Auteur]
Zhejiang University [Hangzhou, China]
Ramon, Jan [Auteur]
Machine Learning in Information Networks [MAGNET]

Éditeur(s) ou directeur(s) scientifique(s) :

Steve Hanneke
Lev Reyzin

Titre de la manifestation scientifique :

ALT 2017 - 28th conference on Algorithmic Learning Theory

Ville :

Kyoto

Pays :

Japon

Date de début de la manifestation scientifique :

2017-10-15

Date de publication :

2017

Mot(s)-clé(s) en anglais :

Non-iid Sample
Networked Example
Concentration Inequality
Sample Error Bound
Generalization Error Bound

Discipline(s) HAL :

Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Théorie de l'information [cs.IT]
Mathématiques [math]/Statistiques [math.ST]
Physique [physics]/Physique [physics]/Analyse de données, Statistiques et Probabilités [physics.data-an]
Statistiques [stat]/Machine Learning [stat.ML]

Résumé en anglais : [en]

Many machine learning algorithms are based on the assumption that training examples are drawn independently. However, this assumption does not hold anymore when learning from a networked sample because two or more training ...
Lire la suite >Many machine learning algorithms are based on the assumption that training examples are drawn independently. However, this assumption does not hold anymore when learning from a networked sample because two or more training examples may share some common objects, and hence share the features of these shared objects. We show that the classic approach of ignoring this problem potentially can have a harmful effect on the accuracy of statistics, and then consider alternatives. One of these is to only use independent examples, discarding other information. However, this is clearly suboptimal. We analyze sample error bounds in this networked setting, providing significantly improved results. An important component of our approach is formed by efficient sample weighting schemes, which leads to novel concentration inequalities.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL