Tree boosting is a highly effective and widely used machine learning method.
In this paper, we describe a scalable end-to-end tree boosting system called
XGBoost, which is used widely by data scientists to achieve state-of-the-art
results on many machine learning challenges. We propose a novel sparsity-aware
algorithm for sparse data and weighted quantile sketch for approximate tree
learning. More importantly, we provide insights on cache access patterns, data
compression and sharding to build a scalable tree boosting system. By combining
these insights, XGBoost scales beyond billions of examples using far fewer
resources than existing systems.
%0 Generic
%1 chen2016xgboost
%A Chen, Tianqi
%A Guestrin, Carlos
%D 2016
%K ai boost tree xgboost
%R 10.1145/2939672.2939785
%T XGBoost: A Scalable Tree Boosting System
%U http://arxiv.org/abs/1603.02754
%X Tree boosting is a highly effective and widely used machine learning method.
In this paper, we describe a scalable end-to-end tree boosting system called
XGBoost, which is used widely by data scientists to achieve state-of-the-art
results on many machine learning challenges. We propose a novel sparsity-aware
algorithm for sparse data and weighted quantile sketch for approximate tree
learning. More importantly, we provide insights on cache access patterns, data
compression and sharding to build a scalable tree boosting system. By combining
these insights, XGBoost scales beyond billions of examples using far fewer
resources than existing systems.
@misc{chen2016xgboost,
abstract = {Tree boosting is a highly effective and widely used machine learning method.
In this paper, we describe a scalable end-to-end tree boosting system called
XGBoost, which is used widely by data scientists to achieve state-of-the-art
results on many machine learning challenges. We propose a novel sparsity-aware
algorithm for sparse data and weighted quantile sketch for approximate tree
learning. More importantly, we provide insights on cache access patterns, data
compression and sharding to build a scalable tree boosting system. By combining
these insights, XGBoost scales beyond billions of examples using far fewer
resources than existing systems.},
added-at = {2021-02-13T13:49:01.000+0100},
author = {Chen, Tianqi and Guestrin, Carlos},
biburl = {https://www.bibsonomy.org/bibtex/252bab0edcc868d4c831b85859ad7f0c1/louissf},
description = {XGBoost: A Scalable Tree Boosting System},
doi = {10.1145/2939672.2939785},
interhash = {f686ba00eda9a53bd2175fbe3f242c71},
intrahash = {52bab0edcc868d4c831b85859ad7f0c1},
keywords = {ai boost tree xgboost},
note = {cite arxiv:1603.02754Comment: KDD'16 changed all figures to type1},
timestamp = {2021-02-13T13:49:01.000+0100},
title = {XGBoost: A Scalable Tree Boosting System},
url = {http://arxiv.org/abs/1603.02754},
year = 2016
}