Learning with Deep Cascades

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 data-dependent theoretical guarantees for learning with Deep Cascades with complex leaf predictors and node questions in terms of the Rademacher complexities of the sub-families composing these sets of predictors and the fraction of sample points reaching each leaf that are correctly classified. These 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.

Cite

Text

DeSalvo et al. "Learning with Deep Cascades." International Conference on Algorithmic Learning Theory, 2015. doi:10.1007/978-3-319-24486-0_17

Markdown

[DeSalvo et al. "Learning with Deep Cascades." International Conference on Algorithmic Learning Theory, 2015.](https://mlanthology.org/alt/2015/desalvo2015alt-learning/) doi:10.1007/978-3-319-24486-0_17

BibTeX

@inproceedings{desalvo2015alt-learning,
  title     = {{Learning with Deep Cascades}},
  author    = {DeSalvo, Giulia and Mohri, Mehryar and Syed, Umar},
  booktitle = {International Conference on Algorithmic Learning Theory},
  year      = {2015},
  pages     = {254-269},
  doi       = {10.1007/978-3-319-24486-0_17},
  url       = {https://mlanthology.org/alt/2015/desalvo2015alt-learning/}
}