Computer Science – Learning
Scientific paper
2005-02-03
Computer Science
Learning
14 pages, 0 figures, 1 class file
Scientific paper
We discuss stability for a class of learning algorithms with respect to noisy labels. The algorithms we consider are for regression, and they involve the minimization of regularized risk functionals, such as L(f) := 1/N sum_i (f(x_i)-y_i)^2+ lambda ||f||_H^2. We shall call the algorithm `stable' if, when y_i is a noisy version of f*(x_i) for some function f* in H, the output of the algorithm converges to f* as the regularization term and noise simultaneously vanish. We consider two flavors of this problem, one where a data set of N points remains fixed, and the other where N -> infinity. For the case where N -> infinity, we give conditions for convergence to f_E (the function which is the expectation of y(x) for each x), as lambda -> 0. For the fixed N case, we describe the limiting 'non-noisy', 'non-regularized' function f*, and give conditions for convergence. In the process, we develop a set of tools for dealing with functionals such as L(f), which are applicable to many other problems in learning theory.
No associations
LandOfFree
Stability Analysis for Regularized Least Squares Regression 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 Stability Analysis for Regularized Least Squares Regression, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Stability Analysis for Regularized Least Squares Regression will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-177152