Udvidet returret til d. 31. januar 2025

Statistical Learning Theory and Stochastic Optimization

Bag om Statistical Learning Theory and Stochastic Optimization

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.

Vis mere
  • Sprog:
  • Engelsk
  • ISBN:
  • 9783540225720
  • Indbinding:
  • Paperback
  • Sideantal:
  • 292
  • Udgivet:
  • 25. august 2004
  • Størrelse:
  • 155x16x235 mm.
  • Vægt:
  • 446 g.
  • BLACK WEEK
Leveringstid: 8-11 hverdage
Forventet levering: 10. december 2024

Beskrivelse af Statistical Learning Theory and Stochastic Optimization

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.

Brugerbedømmelser af Statistical Learning Theory and Stochastic Optimization



Gør som tusindvis af andre bogelskere

Tilmeld dig nyhedsbrevet og få gode tilbud og inspiration til din næste læsning.