2013:
A. Carpentier and A.K.H. Kim. Adaptive and minimax optimal estimation of the tail coefficient. Technical Report arXiv: arXiv:1309.2585, 2013.
arXiv
A. Carpentier. Honest and adaptive confidence sets in Lp. Technical Report arXiv:1306.5899, 2013.
arXiv
A. Carpentier. Testing the regularity of a smooth signal. Technical Report arXiv:1304.2592, 2013.
arXiv
A. Carpentier and R. Munos. Toward Optimal Stratification for Stratified Monte-Carlo Integration (detailed version). Technical Report arXiv:1303.2892, 2013.
.pdf arXiv
2012:
A. Carpentier. De l’échantillonnage optimal en grande et petite dimension. PhD Thesis,
AFIA ex-aequo accessit 2013, (french machine learning/artificial intelligence second price).
.pdf
A. Carpentier and R. Munos. Adaptive Stratified Sampling for Monte-Carlo integration of Differentiable functions (detailed version). Technical Report arXiv:1210.5345, 2012.
.pdf arXiv
O. A. Maillard, and A. Carpentier. Online allocation and homogeneous partitioning for piecewise constant mean-approximation (detailed version). Technical Report hal-00742893, INRIA, 2012.
.pdf HAL
A. Carpentier and R. Munos. Minimax Number of Strata for Online Stratified Sampling given Noisy Samples (detailed version). Technical Report inria-00698517, INRIA, 2012.
.pdf HAL
A. Carpentier and R. Munos. Bandit Theory meets Compressed Sensing for high dimensional Stochastic Linear Bandit (detailed version). Technical Report arXiv:1205.4094 2012.
.pdf arXiv
2011:
A. Carpentier, R. Munos and A. Antos. Minimax strategy for Stratified Sampling for Monte Carlo. Technical Report inria-00636924, INRIA, 2011.
.pdf HAL
A. Carpentier, A. Lazaric, M. Ghavamzadeh, R. Munos and P. Auer. Upper Confidence Bounds Algorithms for Active Learning in Multi-Armed Bandits (detailed version). Technical Report inria-00659696, INRIA, 2011.
.pdf HAL