Goto

Collaborating Authors

 dgcv

Optimal tuning for divide-and-conquer kernel ridge regression with massive data

Xu, Ganggang, Shang, Zuofeng, Cheng, Guang

arXiv.org Machine Learning

We propose a first data-driven tuning procedure for divide-and-conquer kernel ridge regression (Zhang et al., 2015). While the proposed criterion is computationally scalable for massive data sets, it is also shown to be asymptotically optimal under mild conditions. The effectiveness of our method is illustrated by extensive simulations and an application to Million Song Dataset. Some key words:Distributed GCV, divide-and-conquer, kernel ridge regression, optimal tuning.

1612.05907
  Country:
  Genre: Research Report (0.40)
  Technology:

Add feedback