On optimal Sampling in low and high dimension

Alexandra Carpentier 1
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal, Inria Lille - Nord Europe
Abstract : During my PhD, I had the chance to learn and work under the great supervision of my advisor R emi (Munos) in two elds that are of particular interest to me. These domains are Bandit Theory and Compressed Sensing. While studying these domains I came to the conclusion that they are connected if one looks at them trough the prism of optimal sampling. Both these elds are concerned with strategies on how to sample the space in an e cient way: Bandit Theory in low dimension, and Compressed Sensing in high dimension. In this Dissertation, I present most of the work my co-authors and I produced during the three years that my PhD lasted.
Complete list of metadatas

Cited literature [96 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-00844361
Contributor : Philippe Preux <>
Submitted on : Monday, July 15, 2013 - 10:10:15 AM
Last modification on : Thursday, February 21, 2019 - 10:52:49 AM
Long-term archiving on : Wednesday, October 16, 2013 - 4:14:13 AM

Identifiers

  • HAL Id : tel-00844361, version 1

Citation

Alexandra Carpentier. On optimal Sampling in low and high dimension. Statistics [math.ST]. Université des Sciences et Technologie de Lille - Lille I, 2012. English. ⟨tel-00844361⟩

Share

Metrics

Record views

526

Files downloads

1174