Review for NeurIPS paper: Learning with Operator-valued Kernels in Reproducing Kernel Krein Spaces

Summary and Contributions: Post-rebuttal comments Thank you for the comments. I am happy with the response and would recommend including the paragraph (stabilization vs ERM) from the rebuttal into the final version of the paper. It might be interesting as an open problem for future work. Operator valued kernels provide a theoretical framework for modelling learning problems that map functions to functions. A potential shortcoming of this framework is the fact that kernels need to be positive definite.