Why only MNIST and a Graph CNN? Those are small and somewhat odd choices. Scale these days should be at least 100 million param models and something like OpenWebText as a dataset in my opinion. Not sure what the SoTA is for visionm but same argument there.
This paper is from a small group at an academic institution. They are trying to innovate in the idea space and are probably quite compute constrained. But for proving ideas smaller problems can make easier analysis even leaving aside compute resources. Not all research can jump straight to SOTA applications. It looks quite interesting, and I wouldn't be surprised to see it applied soon to larger problems.
Baseline time to grok something looks to be around 1000x normal training time so make that $20k per attempt. Probably takes a while too. Their headline number (50x faster than baseline, $400) looks pretty doable if you can make grokking happen reliably at that speed.
I’ve been in a small group at an academic institution. With our meager resources we trained larger models than this on many different vision problems. I personally train LLMs on OpenWebText than this using a few 4090s (not work related). Is that too much for a small group?
MNIST is solvable using two pixels. It shouldn’t be one of two benchmarks in a paper, again just in my opinion. It’s useful for debugging only.
I thought so at first, but the repo's[0] owner and the first name listed in the article has Seoul National University on their Github profile.
Far away from a small academic institution.
Oh hm, so they are. I thought they were binary because they used a digital pen to create them, IIRC, and logistic regression is always the baseline; but checking, they technically are grayscale and people don't always binarize them. So I guess information-theoretically, if they are 0-255 valued, then 2 pixels could potentially let you classify pretty well if sufficiently pathological.
Grokking may not even occur for datasets of that scale. Even the MNIST experiments require dropping the training data size from 50k examples to 1k. The reason for this is that the phenomenon seems to occur at a critical zone of having just barely enough training data to make generalization possible. See https://arxiv.org/abs/2205.10343 for details.
Even figuring out how to induce grokking behavior on a 100M model or OpenWebText would be a big leap in the understanding of grokking. It's perfectly reasonable for a paper like this to show results on the standard tasks for which grokking has already been characterized.
It’s because that’s where the effect is showing upright now. This is the situation where the analogy to pre-paradigmatic optics is pretty strong. If you telescope to take pictures of Jupiter was having problems with rainbow fringes, so you designed the defraction grading to investigate the fringes
Several reasons - computational effort, effort it takes to reproduce results on complex datasets, academic publishing model.
Academic research is often times about making incremental steps and limiting uncertainty.
Making something work for MNIST is already so much work, researchers don’t have the time, money, and energy to run experiments for 10 datasets.
Complex datasets are much harder to get a proper model trained on due to increased complexity - larger images, tasks, classes, etc.
Also, as soon as you run your experiments on more datasets, you create an opportunity for reviewers to take you down - “why didn’t you test it on this other dataset?”
