Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

eps_theta和eps实验和理论不匹配问题 #2

Open
myu1999 opened this issue Jul 14, 2024 · 0 comments
Open

eps_theta和eps实验和理论不匹配问题 #2

myu1999 opened this issue Jul 14, 2024 · 0 comments

Comments

@myu1999
Copy link

myu1999 commented Jul 14, 2024

您好作者,您在论文中推出反向推理阶段的eps_theta的二范数总是比相同时间步下前向训练阶段的eps(注意您在推导的时候是和前向加噪的eps做对比,并不是用eps_theta(xt, t)作对比)的二范数总是要大一部分,但是根据您论文中的实验图展示,eps_theta是有一个明显下降趋势的,而前向x0到xt阶段的噪声eps一定是一个标准高斯,那么由卡方分布(每个像素点位独立同分布标准高斯,那么其平方和就服从卡方分布)知,eps的二范数期望是一个恒定值。但是eps_theta的下降趋势表明,eps_theta的二范数并不是处处都大于标准高斯eps的二范数。请问作者这一处理论和实验不匹配是怎么回事,特此请教。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant