|
|
|
|
LEADER |
02823nmm a2200397 u 4500 |
001 |
EB000655786 |
003 |
EBX01000000000000000508868 |
005 |
00000000000000.0 |
007 |
cr||||||||||||||||||||| |
008 |
140122 ||| eng |
020 |
|
|
|a 9783540445074
|
100 |
1 |
|
|a Catoni, Olivier
|
245 |
0 |
0 |
|a Statistical Learning Theory and Stochastic Optimization
|h Elektronische Ressource
|b Ecole d'Eté de Probabilités de Saint-Flour XXXI - 2001
|c by Olivier Catoni ; edited by Jean Picard
|
250 |
|
|
|a 1st ed. 2004
|
260 |
|
|
|a Berlin, Heidelberg
|b Springer Berlin Heidelberg
|c 2004, 2004
|
300 |
|
|
|a VIII, 284 p
|b online resource
|
505 |
0 |
|
|a Universal Lossless Data Compression -- Links Between Data Compression and Statistical Estimation -- Non Cumulated Mean Risk -- Gibbs Estimators -- Randomized Estimators and Empirical Complexity -- Deviation Inequalities -- Markov Chains with Exponential Transitions -- References -- Index
|
653 |
|
|
|a Optimization
|
653 |
|
|
|a Information and Communication, Circuits
|
653 |
|
|
|a Statistical Theory and Methods
|
653 |
|
|
|a Statistics
|
653 |
|
|
|a Artificial Intelligence
|
653 |
|
|
|a Information theory
|
653 |
|
|
|a Artificial intelligence
|
653 |
|
|
|a Numerical analysis
|
653 |
|
|
|a Numerical Analysis
|
653 |
|
|
|a Mathematical optimization
|
653 |
|
|
|a Probability Theory and Stochastic Processes
|
653 |
|
|
|a Probabilities
|
700 |
1 |
|
|a Picard, Jean
|e [editor]
|
041 |
0 |
7 |
|a eng
|2 ISO 639-2
|
989 |
|
|
|b SBA
|a Springer Book Archives -2004
|
490 |
0 |
|
|a École d'Été de Probabilités de Saint-Flour
|
856 |
4 |
0 |
|u https://doi.org/10.1007/b99352?nosfx=y
|x Verlag
|3 Volltext
|
082 |
0 |
|
|a 519.2
|
520 |
|
|
|a Statistical learning theory is aimed at analyzing complex data with necessarily approximate models. This book is intended for an audience with a graduate background in probability theory and statistics. It will be useful to any reader wondering why it may be a good idea, to use as is often done in practice a notoriously "wrong'' (i.e. over-simplified) model to predict, estimate or classify. This point of view takes its roots in three fields: information theory, statistical mechanics, and PAC-Bayesian theorems. Results on the large deviations of trajectories of Markov chains with rare transitions are also included. They are meant to provide a better understanding of stochastic optimization algorithms of common use in computing estimators. The author focuses on non-asymptotic bounds of the statistical risk, allowing one to choose adaptively between rich and structured families of models and corresponding estimators. Two mathematical objects pervade the book: entropy and Gibbs measures. The goal is to show how to turn them into versatile and efficient technical tools, that will stimulate further studies and results
|