1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
|
@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",
}
@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",
month="Juillet",
}
@conference{conv,
title="Online Convex Optimization in the Bandit Setting: Gradient Descent Without a Gradient",
author="Abie Flaxman and Adam Tauman Kalai and Brendan McMahan",
booktitle="Proceedings of the Sixteenth Annual ACM-SIAM Symposium on Discrete Algorithms",
year="2005",
}
@unpublished{exp4,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@unpublished{audbu,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"
}
@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"
}
|
