You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thanks for your nice work, and it's experimental results are really impressive.
I notice the values of theta are actually different in paper and source code. From equation 17 in the paper, theta should be 0.001 * d^{-3/2} under the l2 constriant. However, in the source code, theta is set to 1 * d^{-3/2} in this newer commit or 0.01 * d^{-1/2} in this older commit
The text was updated successfully, but these errors were encountered:
Initially theta = 0.01 * d^{-1/2} was used for all the experiments. In the current version of the preprint, we added an improved version of Theorem 2, which explicitly suggests the choice of delta as a function of d. Thus, we redefine theta = 1 * d^{-3/2}.
However, somehow I forgot to change 0.001 to 1. Please use the choice of theta in the new commit as the default one. I will update theta in the future version of preprint.
Hi Jianbo,
Thanks for your nice work, and it's experimental results are really impressive.
I notice the values of theta are actually different in paper and source code. From equation 17 in the paper, theta should be 0.001 * d^{-3/2} under the l2 constriant. However, in the source code, theta is set to 1 * d^{-3/2} in this newer commit or 0.01 * d^{-1/2} in this older commit
The text was updated successfully, but these errors were encountered: