Title :

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

Author(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

Journal title :

Entropy

Publisher :

MDPI

Publication date :

2021

ISSN :

1099-4300

HAL domain(s) :

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

English abstract : [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 ...
Show more >"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?Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

ANR Project :

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

Collections :

• Laboratoire Paul Painlevé - UMR 8524

Source :

Harvested from HAL