Popular decision tree algorithms are provably noise tolerant

Guy Blanc · Jane Lange · Ali Malik · Li-Yang Tan

Hall E #1122

Keywords: [ T: Learning Theory ]

[ Abstract ]
[ Paper PDF
Wed 20 Jul 3:30 p.m. PDT — 5:30 p.m. PDT
Spotlight presentation: T: Learning Theory/Domain Adaptation
Wed 20 Jul 7:30 a.m. PDT — 9 a.m. PDT


Using the framework of boosting, we prove that all impurity-based decision tree learning algorithms, including the classic ID3, C4.5, and CART, are highly noise tolerant. Our guarantees hold under the strongest noise model of nasty noise, and we provide near-matching upper and lower bounds on the allowable noise rate. We further show that these algorithms, which are simple and have long been central to everyday machine learning, enjoy provable guarantees in the noisy setting that are unmatched by existing algorithms in the theoretical literature on decision tree learning. Taken together, our results add to an ongoing line of research that seeks to place the empirical success of these practical decision tree algorithms on firm theoretical footing.

Chat is not available.