Yingda Yin
Yingda Yin
Thanks for your really quick response! Of course, it is https://yingda.notion.site/test-902aa1a64b1a4bbdae9ac6981ea9168b
Hi! Thanks for the response. I got you, but still, building an explicit `build and test` may lower the difficulty for new comers (like me). Actually, I finally refered to...
Yes! I also request this feature for the similar reason
The $\lambda$ is rendered somehow, but with an improper formatting. If possible, can you remove the trailing `$\lambda$ 1` and only retain the unrendered code `\lambda_1`? This is also what...
Many thanks!
Hi, thanks for your interest. The supervised loss in the code is the negative log-likelihood, the same as the paper. It is defined at https://github.com/yd-yin/FisherMatch/blob/main/fisher/fisher_utils.py#L19 Why do you think it...
Given $p(R;A) = \frac{1}{F(A)}\exp(tr(A^TR))$, $-\log(p)=\log(F(A))-tr(A^TR)$, `log_normalizer` is $\log(F)$, `log_exponent` is $-tr(A^TR)$. `overreg` is very close to 1, which is used to better stabilize the training. This term is proposed in...