1cb524b5a3f3f82be4a7d954063c07e2-AuthorFeedback.pdf

We thank all reviewers for their careful reading and useful comments. In particular, we notice Assumption 3.1 and Assumption 3.3 drew most attentions. SGD converges (and recovers the true noise) in correlated settings. Section 4.3.1 in Rasmussen, C. E. (2003), "Gaussian processes in machine learning", which is commonly We will include these results in the camera-ready version if accepted. First we explain the role of "correlation": here we mean the correlation of (k 1) (k 1) (k 1) ( k 1) In order to have a lower bound on the approximate curvature (see Lemma 4.2) that is independent of The proof for Lemma 4.1 is also non-trivial since the error bounds holds uniformly for all We apply Taylor's expansion and a novel truncation technique to avoid the difficulty caused