4e87337f366f72daa424dae11df0538c-AuthorFeedback.pdf

Rebuttal for "Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradients" Provide a more fine-grained analysis. We hope the reviewer will appreciate the merits of this analysis. Analysis does not apply to neural networks. Convergence analysis of nonconvex nonsmooth objectives is important, and is included in our future research agenda. A discussion with these references will be added.