Statistical learning theory and stochastic optimization. Ecole d'Eté de Probabilitiés de Saint-Flour XXXI -- 2001. (Q1880598)
From MaRDI portal
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Statistical learning theory and stochastic optimization. Ecole d'Eté de Probabilitiés de Saint-Flour XXXI -- 2001. |
scientific article |
Statements
Statistical learning theory and stochastic optimization. Ecole d'Eté de Probabilitiés de Saint-Flour XXXI -- 2001. (English)
0 references
30 September 2004
0 references
The main topic of the book is to estimate a probability distribution from observed samples. A risk function of the Kullback divergence type is considered. Other types of risk functions are also considered. Oracle inequalities are associated to estimators restricted to a (possibly random) parametrization. The goal is to bound the unresticted risk by the restricted one plus a term quantifying the complexity of the parametric model. The first chapters give connections with coding theory, universal lossless data compression, and pattern recognition. Then several types of oracle inequalities are studied. Finally, some connections with simulated annealing are investigated. 90 references and an index are provided at the end. This book is an advanced study and accessibility to a broader readership could be improved.
0 references
statistical learning
0 references
Gibbs estimators
0 references
Markov chains
0 references
adaptive classification
0 references
least-squares regression
0 references
probability distribution
0 references
risk function
0 references
Kullback divergence
0 references
oracle inequalities
0 references
estimators
0 references
coding theory
0 references
pattern recognition
0 references
simulated annealing
0 references
