ON LEARNING RATES FOR REGULARIZED NYSTROM SUBSAMPLING IN UNSUPERVISED DOMAIN ADAPTATION

The regularized Nystrom subsampling is a popular approach for learning problems that deals with big data. We employ such technique in the context of the unsupervised domain adaptation problems with covariate shift assumption. Within the framework of the Reproducing Kernel Hilbert Space concept, an algorithm is constructed that is a combination of the Nystrom subsampling and the two-steps iterated Tikhonov regularization. This approach allows significantly reduce the amount of computing resources involved and at the same time maintains the same learning rates as for the standard machine learning algorithms.