Learning with Deep Cascades
Venue
Proceedings of the Twenty-Sixth International Conference on Algorithmic Learning Theory (ALT 2015)
Publication Year
2015
Authors
Giulia DeSalvo, Mehryar Mohri, Umar Syed
BibTeX
Abstract
We introduce a broad learning model formed by cascades of predictors, Deep
Cascades, that is structured as general decision trees in which leaf predictors or
node questions may be members of rich function families. We present new detailed
data-dependent theoretical guarantees for learning with Deep Cascades with complex
leaf predictors or node question in terms of the Rademacher complexities of the
sub-families composing these sets of predictors and the fraction of sample points
correctly classified at each leaf. These general guarantees can guide the design of
a variety of different algorithms for deep cascade models and we give a detailed
description of two such algorithms. Our second algorithm uses as node and leaf
classifiers SVM predictors and we report the results of experiments comparing its
performance with that of SVM combined with polynomial kernels.
