google

/

ddpm-cifar10-32

like 72

Follow

Google 31.1k

\n\nx_0 is as I understand from real data distribution that could not be Gaussian.\nx_t is a combination of x_0 distribution and Gaussian distribution parametrised by β_t.\n\nSimilarly in the DDIM is not the proof behind the mean and variance definition:\n\n\nThanks.","html":"

Hi,

\n

exists any proof for these equations?

\n\n\n

I understand it as condition probability with multiple conditions, that is defined as:

\n

x_0 is as I understand from real data distribution that could not be Gaussian.
x_t is a combination of x_0 distribution and Gaussian distribution parametrised by β_t.

\n

Similarly in the DDIM is not the proof behind the mean and variance definition:

\n

Thanks.

\n","updatedAt":"2024-09-12T10:58:13.479Z","author":{"_id":"642f0983aa1dd0ebdf3c1c1c","avatarUrl":"/avatars/acc0a327882a95676277c168b8c23c74.svg","fullname":"Martin Kubovcik","name":"markub3327","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false}},"numEdits":1,"identifiedLanguage":{"language":"en","probability":0.7536921501159668},"editors":["markub3327"],"editorAvatarUrls":["/avatars/acc0a327882a95676277c168b8c23c74.svg"],"reactions":[],"isReport":false}}],"pinned":false,"locked":false,"collection":"discussions","isPullRequest":false,"isReport":false},"primaryEmailConfirmed":false,"repo":{"name":"google/ddpm-cifar10-32","type":"model"},"discussionRole":0,"acceptLanguages":["*"],"hideComments":true,"repoDiscussionsLocked":false,"isDiscussionAuthor":false}">