DOAJ Open Access 2022

AddGBoost: A gradient boosting-style algorithm based on strong learners

Moshe Sipper Jason H. Moore

Abstrak

We present AddGBoost, a gradient boosting-style algorithm, wherein the decision tree is replaced by a succession of (possibly) stronger learners, which are optimized via a state-of-the-art hyperparameter optimizer. Through experiments over 90 regression datasets we show that AddGBoost emerges as the top performer for 33% (with 2 stages) up to 42% (with 5 stages) of the datasets, when compared with seven well-known machine-learning algorithms: KernelRidge, LassoLars, SGDRegressor, LinearSVR, DecisionTreeRegressor, HistGradientBoostingRegressor, and LGBMRegressor.

Topik & Kata Kunci

Cybernetics Electronic computers. Computer science

Penulis (2)

Moshe Sipper

Jason H. Moore

Format Sitasi

APA MLA BibTeX

Sipper, M., Moore, J.H. (2022). AddGBoost: A gradient boosting-style algorithm based on strong learners. https://doi.org/10.1016/j.mlwa.2021.100243

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →

Lihat di Sumber doi.org/10.1016/j.mlwa.2021.100243

Informasi Jurnal

Tahun Terbit: 2022
Sumber Database: DOAJ
DOI: 10.1016/j.mlwa.2021.100243
Akses: Open Access ✓