Timezone: »
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.
Author Information
Guy Blanc (Stanford University)
Jane Lange (MIT)
Ali Malik (Stanford Universtiy)
Li-Yang Tan (Stanford University)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Poster: Popular decision tree algorithms are provably noise tolerant »
Wed. Jul 20th through Thu the 21st Room Hall E #1122
More from the Same Authors
-
2022 Poster: A query-optimal algorithm for finding counterfactuals »
Guy Blanc · Caleb Koch · Jane Lange · Li-Yang Tan -
2022 Spotlight: A query-optimal algorithm for finding counterfactuals »
Guy Blanc · Caleb Koch · Jane Lange · Li-Yang Tan -
2020 Poster: Provable guarantees for decision tree induction: the agnostic setting »
Guy Blanc · Jane Lange · Li-Yang Tan -
2019 Poster: Calibrated Model-Based Deep Reinforcement Learning »
Ali Malik · Volodymyr Kuleshov · Jiaming Song · Danny Nemer · Harlan Seymour · Stefano Ermon -
2019 Oral: Calibrated Model-Based Deep Reinforcement Learning »
Ali Malik · Volodymyr Kuleshov · Jiaming Song · Danny Nemer · Harlan Seymour · Stefano Ermon