d0f5edad9ac19abed9e235c0fe0aa59f-AuthorFeedback.pdf

As you also noted, the source condition and the eigenvalue decay are fairly standard in the4 nonparametric regression setting. Hence,ourrateimproves8 the known rates for "difficult" problems with loweffectivedimension. Our final comments on the bias of the community towards "weak assumptions" was14 exactly toprovokeadiscussion inthis sense and abetter judgment onthese issues, rather than justifying our results.15 So, we are happy that the reviewer engaged with us in this discussion! Instead, we just consider itan interesting setting that researchers haveignored for along time.18