4 Concluding Remarks
In this paper, we have derived the minimax rate of of regularized least squares for functional linear regression. Our required assumptions are more general and realistic than those in the literature. On the other hand, we focus on scalar response in the functional linear model. It would be interesting to consider multiple responses arising from multilinear model and study the corresponding regularized least squares setting as a future research work. Such a setting can have useful applications in image and multi-dimensional signal processing.
