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
I think with the current code that the two terms in g_lb_inference have a different scaling. The T.sum reduces dg(L_corr) * log_qz_given_x to a single number, which is then broadcast across all the elements of L, which has dimensions batchsize x eq_samples. So the second term is scaled by 1/ (batchsize * eq_samples), whereas this term cancels in the first term because it is summed that many times
The text was updated successfully, but these errors were encountered:
Should the following line,
https://github.com/casperkaae/parmesan/blob/master/examples/vimco.py#L248
actually read
g_lb_inference = T.mean(T.sum(dg(L_corr) * log_qz_given_x, axis=2) + L)
instead of
g_lb_inference = T.mean(T.sum(dg(L_corr) * log_qz_given_x) + L)
?
I think with the current code that the two terms in
g_lb_inference
have a different scaling. TheT.sum
reducesdg(L_corr) * log_qz_given_x
to a single number, which is then broadcast across all the elements ofL
, which has dimensions batchsize x eq_samples. So the second term is scaled by 1/ (batchsize * eq_samples), whereas this term cancels in the first term because it is summed that many timesThe text was updated successfully, but these errors were encountered: