Machine Learning

1 readers

1 users here now

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

founded 1 year ago

MODERATORS

communick@academy.garden

[D] Logit Laplace Reconstruction Loss (alien.top)

submitted 1 year ago by clywac2@alien.top to c/machinelearning@academy.garden

3 comments fedilink hide all child comments

Was reading through the original DALL-E paper (https://arxiv.org/pdf/2102.12092.pdf) and found their appendix A.3 pretty interesting. The motivation behind the logit Laplace loss totally makes sense, but if you plot the negative log of the PDF of their logit Laplace function, it's not strictly positive as a function of x. Does that mean the authors are allowing for a potentially negative loss with this reformulation?

you are viewing a single comment's thread
view the rest of the comments

[–] mrfox321@alien.top 1 points 1 year ago (1 children)

Objective functions can be negative. What is the issue?

[–] clywac2@alien.top 1 points 1 year ago

it's just every other assumed prior (Gaussian, Laplacian) for the reconstruction error gives strictly nonnegative errors when the negative log is taken, so I expected this one to as well