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] Why are ML model outputs not tested regarding statistical significance? (alien.top)

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

57 comments fedilink hide all child comments

Often when I read ML papers the authors compare their results against a benchmark (e.g. using RMSE, accuracy, ...) and say "our results improved with our new method by X%". Nobody makes a significance test if the new method Y outperforms benchmark Z. Is there a reason why? Especially when you break your results down e.g. to the anaylsis of certain classes in object classification this seems important for me. Or do I overlook something?

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

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

Old papers were doing so. Yet now that we decided that NN are bricks that should be trained leaving no data out, we do not care about statistical significance anymore. Anyway test set is probably partially included in the training set of the fondation model you downloaded. It started with Deepmind and RL where experiments where very expensive to run (Joelle Pineau had a nice talk about theses issues). Yet as alpha_whatever are undeniable successes researcher pursued this path. Now go for useless confidence intervals when a training is worth 100 millions in compute... Nah, better rate the outputs by a bunch of humans.