Reviews: Generalization in multitask deep neural classifiers: a statistical physics approach

The experiments on multitask learning are informative. I wish the experiments and theory were a bit more integrated. See my comments below for more details. The authors moved a lot of details to the appendix while keeping the main conclusions in the main submission to ease understanding. Here are some examples: (a) L181-184 what equation shows (s_A - \tilde{s_A}) depends on the said 4 things; (b) L185-186 when labelled data is scarce why is (\bar{s_A*g(s_A)}-\tilde{s_A*g(s_A)} 0; (c) L189-190 why does (\bar{s_A*g(s_A)}-\tilde{s_A*g(s_A)} tend to 0 when training data is abundant.