reviewers in each paragraph as follows

We sincerely thank the reviewers for their time and constructive comments. According to our complexity study in Theorem 1 and Section 3.2, maintaining a small active set is The correlation between features may affect the efficiency of Thunder, but it does not impact the algorithm's safety. According to the derivation in Section 2.1, the stop condition regarding feature recruiting given in Lemma 1 The current algorithm complexity analysis in the supplemental file ignores the sampling steps. The sampling strategy does not reduce or break the algorithm's We will take the reviewers' suggestions and show more results on the effectiveness of sampling. We thank the reviewers again for their insightful comments on writing.