Classification with Minimax Fast Rates for Classes of Bayes Rules with Sparse Representation

Details Classification with Minimax Fast Rates for Classes of Bayes Rules with Sparse Representation Classification with Minimax Fast Rates for Classes of Bayes Rules with Sparse Representation

2006-07-18

arxiv.org/abs/math/0607439v1

Mathematics

Statistics Theory

Scientific paper

We construct a classifier which attains the rate of convergence $\log n/n$ under sparsity and margin assumptions. An approach close to the one met in approximation theory for the estimation of function is used to obtain this result. The idea is to develop the Bayes rule in a fundamental system of $L^2([0,1]^d)$ made of indicator of dyadic sets and to assume that coefficients, equal to $-1,0 {or} 1$, belong to a kind of $L^1-$ball. This assumption can be seen as a sparsity assumption, in the sense that the proportion of coefficients non equal to zero decreases as "frequency" grows. Finally, rates of convergence are obtained by using an usual trade-off between a bias term and a variance term.

Affiliated with

Also associated with

No associations

Rating

Classification with Minimax Fast Rates for Classes of Bayes Rules with Sparse Representation does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Classification with Minimax Fast Rates for Classes of Bayes Rules with Sparse Representation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Classification with Minimax Fast Rates for Classes of Bayes Rules with Sparse Representation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-625604