You are currently offline. Some features of the site may not work correctly.

Corpus ID: 5812807

Learning Theory of Distributed Regression with Bias Corrected Regularization Kernel Network

@article{Guo2017LearningTO,
title={Learning Theory of Distributed Regression with Bias Corrected Regularization Kernel Network},
author={Z. Guo and Lei Shi and Q. Wu},
journal={J. Mach. Learn. Res.},
year={2017},
volume={18},
pages={118:1-118:25}
}

Distributed learning is an effective way to analyze big data. In distributed regression, a typical approach is to divide the big data into multiple blocks, apply a base regression algorithm on each of them, and then simply average the output functions learnt from these blocks. Since the average process will decrease the variance, not the bias, bias correction is expected to improve the learning performance if the base regression algorithm is a biased one. Regularization kernel network is an… Expand