A Few Notes on Statistical Learning Theory

نویسنده

  • Shahar Mendelson
چکیده

2 Glivenko-Cantelli Classes 5 2.1 The classical approach . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.1.1 The symmetrization procedure . . . . . . . . . . . . . . . . . . . . . 7 2.1.2 Covering numbers and complexity estimates . . . . . . . . . . . . . . 9 2.2 Combinatorial parameters and covering numbers . . . . . . . . . . . . . . . 12 2.2.1 Uniform entropy and the VC dimension . . . . . . . . . . . . . . . . 13 2.2.2 Generalized combinatorial parameters . . . . . . . . . . . . . . . . . 16 2.3 Talagrand’s inequality . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 2.4 Random averages, combinatorial parameters and covering numbers . . . . . 21 2.4.1 Structural results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 2.4.2 Example: Kernel Classes . . . . . . . . . . . . . . . . . . . . . . . . 23 2.4.3 Entropy and averages . . . . . . . . . . . . . . . . . . . . . . . . . . 25

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Revision of Coding Theory for Learning from Language

Elements of a quantitative-symbolic theory of human language communication based on power-law entropic sublinearity are induced from independent results in quantitative linguistics, statistical NLP, information theory, plectics, neurosciences and statistical physics.

متن کامل

Statistical Learning and High-dimensional Data

PREFACE This set of notes are used for teaching class " Statistical Learning and High-dimensional Data ". The goal is to give a comprehensive review on statistical learning methods and the methods for handling high-dimensional data. Currently, these appear to be hot areas in statistical fields so I hope that through this course, students can have a sense of what are their foundations and what a...

متن کامل

Information Theory and Statistical Physics - Lecture Notes

This document consists of lecture notes for a graduate course, which focuses on the relations between Information Theory and Statistical Physics. The course is aimed at EE graduate students in the area of Communications and Information Theory, as well as to graduate students in Physics who have basic background in Information Theory. Strong emphasis is given to the analogy and parallelism betwe...

متن کامل

Lecture Notes on Information Theory and Statistical Physics

As the title tells, this paper is based on lecture notes of a graduate course, which focuses on the relations between information theory and statistical physics. The course was delivered at the Technion during the Spring of 2010 for the first time, and its target audience consists of EE graduate students in the area of communications and information theory, as well as graduate students in Physi...

متن کامل

Unsupervised statistical learning underpins computational, behavioural, and neural manifestations of musical expectation

The ability to anticipate forthcoming events has clear evolutionary advantages, and predictive successes or failures often entail significant psychological and physiological consequences. In music perception, the confirmation and violation of expectations are critical to the communication of emotion and aesthetic effects of a composition. Neuroscientific research on musical expectations has foc...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2002