Smart choices on important options

[mchsyu]

In the subsection, under the title A.2 importance features, of the appendix, the article mentioned that based on Table 3, Harmonica concluded that the Initial learning rate of the small network and for the large network is in the range from 0.001 to 0.1. (At stage 1-3, 04. Initial learning rate *05. Initial learning rate (Detail 1))

My question is: how can we conclude this statement from the 4th, 5th and 6th options (Initial learning rate) ? For example, If "-1" stands for "T", (x_4, x_5, x_6)= (-1, -1, -1) means the initial learning rate=0.3. Do I take this right?

If I do, then since Table 3 suggests x_4* x_5 is important, I might get one of the ranges, >= 0.1, [0.01, 0.1], [0.001, 0.01], or <= 0.001.

The paper seemed to locate none of them.

[callowbird]

Thanks. In table 3, the feature 1-5 is X4, which has negative weight, showing that we want X4=1, i.e., learning rate <0.01.
Then, the feature 1-3 is X4X5, with positive weight, showing that we want X4X5=-1, so X5=-1. That is, [0.001,0.01].

Such inference is not necessary in the algorithm, as we simply enumerate all possibilities of all selected hyperparameters.