1 citations · 1 across the 2 of their papers we have counts for
3 papers
Generalization Properties of Decision Trees on Real-valued and Categorical Features
Jean-Samuel Leboeuf, Frédéric LeBlanc, Mario Marchand
We revisit binary decision trees from the perspective of partitions of the data. We introduce the notion of partitioning function, and we relate it to the growth function and to th…
Improving Generalization Bounds for VC Classes Using the Hypergeometric Tail Inversion
Jean-Samuel Leboeuf, Frédéric LeBlanc, Mario Marchand
We significantly improve the generalization bounds for VC classes by using two main ideas. First, we consider the hypergeometric tail inversion to obtain a very tight non-uniform d…
Decision trees as partitioning machines to characterize their generalization properties
Jean-Samuel Leboeuf, Frédéric LeBlanc, Mario Marchand
Decision trees are popular machine learning models that are simple to build and easy to interpret. Even though algorithms to learn decision trees date back to almost 50 years, key…