%0 Generic %1 das2015gaussian %A Das, Sourish %A Roy, Sasanka %A Sambasivan, Rajiv %D 2015 %K regression %T Fast Gaussian Process Regression for Big Data %U http://arxiv.org/abs/1509.05142 %X Gaussian Processes are widely used for regression tasks. A known limitation in the application of Gaussian Processes to regression tasks is that the computation of the solution requires performing a matrix inversion. The solution also requires the storage of a large matrix in memory. These factors restrict the application of Gaussian Process regression to small and moderate size data sets. We present an algorithm based on empirically determined subset selection that works well on both real world and synthetic datasets. On the synthetic and real world datasets used in this study, the algorithm demonstrated sub-linear time and space complexity. The correctness proof for the algorithm is also presented.

@misc{das2015gaussian, abstract = {Gaussian Processes are widely used for regression tasks. A known limitation in the application of Gaussian Processes to regression tasks is that the computation of the solution requires performing a matrix inversion. The solution also requires the storage of a large matrix in memory. These factors restrict the application of Gaussian Process regression to small and moderate size data sets. We present an algorithm based on empirically determined subset selection that works well on both real world and synthetic datasets. On the synthetic and real world datasets used in this study, the algorithm demonstrated sub-linear time and space complexity. The correctness proof for the algorithm is also presented.}, added-at = {2015-09-18T15:10:04.000+0200}, author = {Das, Sourish and Roy, Sasanka and Sambasivan, Rajiv}, biburl = {https://www.bibsonomy.org/bibtex/2a9f8960a4104a78ea8a34129cedc04b7/stdiff}, description = {Fast Gaussian Process Regression for Big Data}, interhash = {6514fbad59a44c38d2887124965fee77}, intrahash = {a9f8960a4104a78ea8a34129cedc04b7}, keywords = {regression}, note = {cite arxiv:1509.05142}, timestamp = {2015-09-18T15:10:04.000+0200}, title = {Fast Gaussian Process Regression for Big Data}, url = {http://arxiv.org/abs/1509.05142}, year = 2015 }