summaryrefslogtreecommitdiffstats
path: root/biblio.bib
diff options
context:
space:
mode:
authorThibaut Horel <thibaut.horel@gmail.com>2010-06-22 01:16:14 +0200
committerThibaut Horel <thibaut.horel@gmail.com>2010-06-22 01:16:14 +0200
commit71b1a44313019a7c58e038d6bb6d2b0aba44ec1f (patch)
tree3ffc0edc6b6cbb398fe79aecb9d8c2fb91a92dc9 /biblio.bib
parent5a3533fa3f2fb02fd3cda2b546549a61b8d0407b (diff)
downloadbandits-71b1a44313019a7c58e038d6bb6d2b0aba44ec1f.tar.gz
Ajout d'une bibliographie. Nombreux ajouts :
- Algorithme UCB - Prédiction convexe avec info totale
Diffstat (limited to 'biblio.bib')
-rw-r--r--biblio.bib95
1 files changed, 95 insertions, 0 deletions
diff --git a/biblio.bib b/biblio.bib
new file mode 100644
index 0000000..a8ecc26
--- /dev/null
+++ b/biblio.bib
@@ -0,0 +1,95 @@
+@book{plg,
+ title="Prediction, learning, and games",
+ author="Cesa-Bianchi, Nicoló and Lugosi, Gàbor",
+ year="2006",
+ publisher="Cambridge University Press"
+}
+
+@conference{zink,
+ title="Online Convex Programming and Generalized Infinitesimal
+Gradient Ascent",
+ author="Zinkevich, Martin",
+ booktitle="Proceedings of The 20th International Conference
+on Machine Learning",
+ year="2003"
+}
+
+@conference{linband,
+ title="Competing in the Dark: An Efficient Algorithm for Bandit Linear
+Optimization ",
+ author="Jacob Abernethy and Elad Hazan and Alexander Rakhlin",
+ booktitle="Proceedings of The 21st Annual Conference on
+Learning Theory",
+ year="2008",
+ month="Juillet",
+}
+
+@unpublished{exp4,
+ title="An Optimal High Probability Algorithm for the Contextual Bandit
+Problem",
+ author="Alina Beygelzimer and John Langford and Lihong Li and Lev Reyzin and
+Robert E. Schapire",
+ note="Publié sur arXiv",
+ year="2010"
+}
+
+@unpublished{audbu,
+ title="Minimax Policies for Bandits Games",
+ author="Jean-Yves Audibert and Sébastien Bubeck",
+ year="2010",
+ note="À paraître"
+}
+
+@article{bandsto,
+ title="Finite time analysis of the multiarmed bandit problem",
+ author="Peter Auer and Cesa-Bianchi, Nicoló and Paul Fischer",
+ journal="Machine Learning",
+ year="2002",
+ volume="47",
+ pages="235--256",
+ number="2/3"
+}
+
+@article{bandet,
+ title="The nonstochastic multiarmed bandit problem",
+ author="Peter Auer and Nicoló Cesa-Bianchi and Yoav Freund and Robert E.
+Schapire",
+ journal="SIAM Journal on Computing",
+ volume="32",
+ number="1",
+ pages="48--77",
+ year="2002"
+}
+
+@conference{multi,
+ title="Optimal Algorithms for Online Convex Optimization with Multi-Point
+Bandit Feedback",
+ author="Alekh Agarwal and Ofer Dekel and Lin Xiao",
+ booktitle="Proceedings of The 23rd Annual Conference on
+Learning Theory",
+ year="2010"
+}
+
+@article{label,
+ title="Minimizing regret with label efficient prediction",
+ author="Cesa-Bianchi, Nicoló and Lugosi, Gàbor and Gilles Stoltz",
+ journal="IEEE Transactions on Information Theory",
+ volume="51",
+ number="6",
+ year="2005",
+ pages="2152--2162"
+}
+
+@book{massart,
+ title="Concentration Inequalities and Model Selection",
+ author="Pascal Massart",
+ series="Lecture Notes in Mathematics",
+ publisher="Springer",
+ note="École d'Eté de Probabilités de Saint-Flour XXXIII -- 2003",
+ year="2007"
+}
+
+
+
+
+