XGBoost: A Scalable Tree Boosting System
koptimizer opened this issue ยท 0 comments
koptimizer commented
๐ ๋ ผ๋ฌธ์ ์ ๋ณด๋ฅผ ์๋ ค์ฃผ์ธ์.
- XGBoost A Scalable Tree Boosting System
- Tianqi Chen & Carlos Guestrin
- KDD '16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
- 2016-08
๐ 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.
๐ ์ด๋ค ๋ ผ๋ฌธ์ธ์ง ์๊ฐํด์ฃผ์ธ์.
- Scalableํ ๋จธ์ ๋ฌ๋ ํ๋ ์์์ธ XGboost์ ๋ํ ๋ ผ๋ฌธ์ ๋๋ค.
- ๊ฒฝ์ง๋ํ๋ ๊ฐ์ข ๋ถ์์์ ๋น์ฐํ๊ฒ ์ป๋ ํ๋ ์์์ด๋ผ์ ๋๋ฐ์ฒด ์ด๋ป๊ฒ ๋ง๋ค์๊ธธ๋ ๊ทธ๋ ๊ฒ ์ฑ๋ฅ์ด ์ข์ ๊ฒ์ธ์ง ํ์ธํด๋ณด๋ ค๊ณ ํฉ๋๋ค.
๐ ํต์ฌ ํค์๋๋ฅผ ์ ์ด์ฃผ์ธ์.
- Scalable, Gradient boosting, Sparsity-aware, parallel