Hi, Thank you for your excellent work!
While searching for width, I wonder whether the operations with different channel numbers share the weight from the one-shot network? If yes, how does the weight in the one-shot network get updated, since it has K(K=2 in your framework figure) gradients separately from the K sampled operation?
Btw, "When τ-> 0, p^ = [^ p1; :::; p^j; :::] becomes one-shot, and the Gumbel-softmax distribution...", do you mean "one-hot" instead of "one-shot"?
Hi, Thank you for your excellent work! While searching for width, I wonder whether the operations with different channel numbers share the weight from the one-shot network? If yes, how does the weight in the one-shot network get updated, since it has K(K=2 in your framework figure) gradients separately from the K sampled operation? Btw, "When τ-> 0, p^ = [^ p1; :::; p^j; :::] becomes one-shot, and the Gumbel-softmax distribution...", do you mean "one-hot" instead of "one-shot"?