Mathematics – Statistics Theory
Scientific paper
2008-03-12
Annals of Statistics 2008, Vol. 36, No. 1, 64-94
Mathematics
Statistics Theory
Published in at http://dx.doi.org/10.1214/009053607000000631 the Annals of Statistics (http://www.imstat.org/aos/) by the Inst
Scientific paper
10.1214/009053607000000631
We consider the problem of approximating a given element $f$ from a Hilbert space $\mathcal{H}$ by means of greedy algorithms and the application of such procedures to the regression problem in statistical learning theory. We improve on the existing theory of convergence rates for both the orthogonal greedy algorithm and the relaxed greedy algorithm, as well as for the forward stepwise projection algorithm. For all these algorithms, we prove convergence results for a variety of function classes and not simply those that are related to the convex hull of the dictionary. We then show how these bounds for convergence rates lead to a new theory for the performance of greedy algorithms in learning. In particular, we build upon the results in [IEEE Trans. Inform. Theory 42 (1996) 2118--2132] to construct learning algorithms based on greedy approximations which are universally consistent and provide provable convergence rates for large classes of functions. The use of greedy algorithms in the context of learning is very appealing since it greatly reduces the computational burden when compared with standard model selection using general dictionaries.
Barron Andrew R.
Cohen Albert
Dahmen Wolfgang
DeVore Ronald A.
No associations
LandOfFree
Approximation and learning by greedy algorithms 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 Approximation and learning by greedy algorithms, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Approximation and learning by greedy algorithms will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-369403