Tree Learning: Optimal Sample Complexity and Algorithms
Dmitrii Avdiukhin, Grigory Yaroslavtsev, Danny Vainstein, Orr Fischer, Sauman Das, Faraz Mirza
Abstract
We study the problem of learning a hierarchical tree representation of data from labeled samples, taken from an arbitrary (and possibly adversarial) distribution. Consider a collection of data tuples labeled according to their hierarchical structure. The smallest number of such tuples required in order to be able to accurately label subsequent tuples is of interest for data collection in machine learning. We present optimal sample complexity bounds for this problem in several learning settings, including (agnostic) PAC learning and online learning. Our results are based on tight bounds of the Natarajan and Littlestone dimensions of the associated problem. The corresponding tree classifiers can be constructed efficiently in near-linear time.
BibTeX
@article{Avdiukhin_Yaroslavtsev_Vainstein_Fischer_Das_Mirza_2023, title={Tree Learning: Optimal Sample Complexity and Algorithms}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/25822}, DOI={10.1609/aaai.v37i6.25822}, abstractNote={We study the problem of learning a hierarchical tree representation of data from labeled samples, taken from an arbitrary (and possibly adversarial) distribution. Consider a collection of data tuples labeled according to their hierarchical structure. The smallest number of such tuples required in order to be able to accurately label subsequent tuples is of interest for data collection in machine learning. We present optimal sample complexity bounds for this problem in several learning settings, including (agnostic) PAC learning and online learning. Our results are based on tight bounds of the Natarajan and Littlestone dimensions of the associated problem. The corresponding tree classifiers can be constructed efficiently in near-linear time.}, number={6}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Avdiukhin, Dmitrii and Yaroslavtsev, Grigory and Vainstein, Danny and Fischer, Orr and Das, Sauman and Mirza, Faraz}, year={2023}, month={Jun.}, pages={6701-6708} }