Concentration inequalities for sampling ...
Document type :
Compte-rendu et recension critique d'ouvrage
DOI :
Title :
Concentration inequalities for sampling without replacement
Author(s) :
Bardenet, Remi [Auteur]
University of Oxford
Maillard, Odalric Ambrym [Auteur]
Department of Electrical Engineering - Technion [Haïfa] [EE-Technion]
Machine Learning and Optimisation [TAO]
University of Oxford
Maillard, Odalric Ambrym [Auteur]
Department of Electrical Engineering - Technion [Haïfa] [EE-Technion]
Machine Learning and Optimisation [TAO]
Journal title :
Bernoulli
Pages :
1361-1385
Publisher :
Bernoulli Society for Mathematical Statistics and Probability
Publication date :
2015
ISSN :
1350-7265
English keyword(s) :
Sampling without replacement
Concentration bounds
Concentration bounds
HAL domain(s) :
Mathématiques [math]/Statistiques [math.ST]
English abstract : [en]
Concentration inequalities quantify the deviation of a random variable from a fixed value. In spite of numerous applications, such as opinion surveys or ecological counting procedures , few concentration results are known ...
Show more >Concentration inequalities quantify the deviation of a random variable from a fixed value. In spite of numerous applications, such as opinion surveys or ecological counting procedures , few concentration results are known for the setting of sampling without replacement from a finite population. Until now, the best general concentration inequality has been a Hoeffding inequality due to ?. In this paper, we first improve on the fundamental result of ?, and further extend it to obtain a Bernstein concentration bound for sampling without replacement. We then derive an empirical version of our bound that does not require the variance to be known to the user.Show less >
Show more >Concentration inequalities quantify the deviation of a random variable from a fixed value. In spite of numerous applications, such as opinion surveys or ecological counting procedures , few concentration results are known for the setting of sampling without replacement from a finite population. Until now, the best general concentration inequality has been a Hoeffding inequality due to ?. In this paper, we first improve on the fundamental result of ?, and further extend it to obtain a Bernstein concentration bound for sampling without replacement. We then derive an empirical version of our bound that does not require the variance to be known to the user.Show less >
Language :
Anglais
Popular science :
Non
Collections :
Source :
Files
- https://hal.archives-ouvertes.fr/hal-01216652/document
- Open access
- Access the document
- https://doi.org/10.3150/14-bej605
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-01216652/document
- Open access
- Access the document
- https://doi.org/10.3150/14-bej605
- Open access
- Access the document
- https://doi.org/10.3150/14-bej605
- Open access
- Access the document
- https://doi.org/10.3150/14-bej605
- Open access
- Access the document
- https://doi.org/10.3150/14-bej605
- Open access
- Access the document
- document
- Open access
- Access the document
- submittedArxiv.pdf
- Open access
- Access the document
- 14-bej605
- Open access
- Access the document