Applications of Vapnik's Theory for Prediction

摘要

Vapnik's work on learning theory has provided a general framework for building efficient predictors. Through the notion of Vapnik-Chervonenkis dimension, we can control the predictor complexity and adapt it to the problem complexity and sample size, while guaranteeing a worst case error bound. In this talk, I will focus on practical issues to see how these results can be used to design efficient predictors on real world problems.