3eb2f1a06667bfb9daba7f7effa0284b-AuthorFeedback.pdf

The first termkxt x αk2 can be simply merged in eq. The first term is consensus error and will be merged inT1 in eq. Response: We have conducted more experiments over the ImageNet37 dataset which is known as a complicated dataset. As the middle figure38 demonstrates, for a binary classification, our method significantly im-39 proves upon the benchmarks over this dataset as well. We also carried40 out experiments on a deeper neural network with 4 hidden layers and41 ourmethod providessignificant speedups overthebenchmarks (bottom42 figure).