Lesson 3: Superlative Processing with XGBoost and GPUs


H2O.ai’s enablement of the gradient boosting library, XGBoost, on rapid performing GPUs have opened up new venues in the field of data science. Data practitioners can now process data and implement machine learning models faster than previously possible.

The following GitHub benchmarks will help you get a better understanding of the performance scenario with the enablement of XGBoost on GPUs:

- GitHub Benchmarks

The concept and its realizaton are aptly captivating and the following video from H2O.ai’s CTO, Arno Candel, puts light on the mechanics that go behind achieving performance improvements of 10x and more. Arno has over a decade of rich experience in spearheading design and implementation of machine learning algorithms.





Questions?

  • We'd love to hear from you! Reach out to us on our Google Stream group with questions, requests, or comments any time.