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
RFF: random_fourier_features_gpu() adds a new dimension of size num_f rather than performs dimension transformation.
lossb_expect(cfeaturec, num_f) computes the square of the Frobenius norm of the original feature vector (of size batch_size * feature_dimemsion ) at each num_f dimension, then accumulating them minus the trace of covariance matrix gives the final loss.
Question:
Does cfeaturec refer to A_i and B_i, and n the batch size in Eq. (3)?
num_f refer to n_A and n_B in Eq. (4)?
The text was updated successfully, but these errors were encountered:
Actually, A and B refer to two variables and and refer to features of the representation, as described in Section 3.1 of the paper. Thus cfeaturec does not refer to A_i and B_i, but (A_1, ..., A_n) and (B_1, ... ,B_n) refer to two variables in cfeature. n refers to the batch size.
Actually, n_A and n_B are twice of num_f, because when we randomly sample one set of w and b for RFF, both sine and cosine of the feature are calculated.
My understanding:
random_fourier_features_gpu()
adds a new dimension of sizenum_f
rather than performs dimension transformation.lossb_expect(cfeaturec, num_f)
computes the square of the Frobenius norm of the original feature vector (of sizebatch_size * feature_dimemsion
) at eachnum_f
dimension, then accumulating them minus the trace of covariance matrix gives the final loss.Question:
cfeaturec
refer toA_i
andB_i
, andn
the batch size in Eq. (3)?num_f
refer ton_A
andn_B
in Eq. (4)?The text was updated successfully, but these errors were encountered: