On Coresets for Regularized Loss Minimization
arXiv: Learning, 2019.
We design and mathematically analyze sampling-based algorithms for regularized loss minimization problems that are implementable in popular computational models for large data, in which the access to the data is restricted in some way. Our main result is that if the regularizer's effect does not become negligible as the norm of the hypo...More
PPT (Upload PPT)