Reviews: Efficient Second-Order Online Kernel Learning with Adaptive Embedding

The paper proposes an efficient second-order online kernel learning mainly by combining KONS and Nystrom method. NOVELTY The novelty is limited on both the methodological and theoretical contributions. The achieved results do not have profound implication for the advancement of theory and practice. WRITING QUALITY The English writing and organization of this paper are relatively good. The reviewer strongly suggests the authors arrange Table 2 in the main paper rather than in Appendix because the experimental results in Table 2 are the core material.