Titre :

Still no free lunches: the price to pay for tighter PAC-Bayes bounds

Auteur(s) :

Guedj, Benjamin [Auteur]
The Inria London Programme [Inria-London]
MOdel for Data Analysis and Learning [MODAL]
Inria-CWI [Inria-CWI]
Department of Computer science [University College of London] [UCL-CS]
University College of London [London] [UCL]
Pujol, Louis [Auteur]
Université Paris-Saclay

Titre de la revue :

Entropy

Éditeur :

MDPI

Date de publication :

2021

ISSN :

1099-4300

Discipline(s) HAL :

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

Résumé en anglais : [en]

"No free lunch" results state the impossibility of obtaining meaningful bounds on the error of a learning algorithm without prior assumptions and modelling. Some models are expensive (strong assumptions, such as as subgaussian ...
Lire la suite >"No free lunch" results state the impossibility of obtaining meaningful bounds on the error of a learning algorithm without prior assumptions and modelling. Some models are expensive (strong assumptions, such as as subgaussian tails), others are cheap (simply finite variance). As it is well known, the more you pay, the more you get: in other words, the most expensive models yield the more interesting bounds. Recent advances in robust statistics have investigated procedures to obtain tight bounds while keeping the cost minimal. The present paper explores and exhibits what the limits are for obtaining tight PAC-Bayes bounds in a robust setting for cheap models, addressing the question: is PAC-Bayes good value for money?Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Projet ANR :

Une Perspective PAC-Bayésienne de l'Apprentissage de Représentations
Apprentissage PAC-bayésien agnostique

Collections :

• Laboratoire Paul Painlevé - UMR 8524

Source :

Harvested from HAL