SupplementaryFile

It is structured as follows. Finally, Appendix E provides the proofs of the results in Sec. 5, including Theorems 5 and 6 which analyze the optimization error, generalization error and excess risk error of the proposedSLRLA. The main limitation of this work is that the analysis in this work cannot be applicable to general nonconvex problems. This is because as explained in Sec. In this way, our analysis cannot be applicable to general nonconvex problems.