Hacker News Reader

Comment by chroem- | Hacker News Reader

> We trained a generative model on CIFAR-10, which we then used to generate ~6 million images. The scale of the dataset was chosen to ensure that it is “virtually infinite” from the model’s perspective, so that the model never resamples the same data.

I don't think so, Tim. They observe identical performance between cifar-10 and cifar-5m, because the generative model for cifar-5m learned to replicate the distribution that cifar-10 was sampled from. It's the same dataset.

View on HN

Note that we also have ImageNet experiments, with entirely real data (non-synthetic). See Section 4, and in particular Figure 3 of the full paper: https://arxiv.org/abs/2010.08127

To clarify some other comments on this post: In all settings, we compare "Real World" and "Ideal World" for the same underlying distribution. Eg, we never compare CIFAR-10 and CIFAR-5m, we only compare "Real World CIFAR-5m" vs "Ideal World CIFAR-5m".

But who actually uses your ImageNet DogBird dataset in an existing study? Part of the problem is that you're inventing your own benchmark. And yet you could have used SVHN and/or the same fixtures (i.e. datasets and ablations) of some of the work you cite e.g. as in "Fantastic Generalization Measures and Where to Find Them" https://arxiv.org/pdf/1912.02178.pdf

The CIFAR-5m result is interesting, but it's misleading to the reader since the dataset is so contrived. And yet you lead with it on your front page. There's wayyyy too much hype going on here.

This looked suspect to me at first as well, but on reflection it doesn't seem so bad. The important aspect here is that they have some large dataset that a model will converge on in less than one epoch. The benefit of generating it from cifar-10 is just that they already have multiple reasonable models to compare with, and they already have the hyperparameters for them.

I haven't read the paper, but my guess is that the 50K images in the real-world epoch are not just real images from the cifar-10 dataset, they're 50K random images from cifar-5m. I'm also guessing they don't ever compare performance between a model trained on cifar-10 vs. cifar-5m, they only compare performance of real vs. ideal. So in effect, you can ignore the cifar-10 dataset.

I've had the opportunity to train on an 88 billion example dataset, and while you do see diminishing returns with each additional sample, it is still important to try to cover as much of the dataset as possible. The limiting factor on training on datasets that large seems to be some sort of hysteresis overfit on the earlier samples that prevents the model from generalizing to the entire dataset. Normally it goes unnoticed, but there is still a small amount of overfit that accumulates the longer you train the model, even if every sample is new.

Thanks this insight helped me understand an issues I'm currently having with training actually!

n = 88 billion is larger than I can think of for any DL research I've read about. Can you (ahem) enlarge on that?

It's an ultra high resolution sales forecast model for a national retailer. It's made somewhat more manageable by the fact that the data is 1D instead of 2D though.

I wonder if that's an important difference? Sales data seems far more noisy and less informative than all of the scaling research datasets I can think of like images or text. It could also just be that you had some minor flaw causing underfitting in your approach like using too-small models which aren't compute-optimal or too much regularization (a critical part of scaling papers is removing standard regularizers like dropout to avoid hobbling the model).

I've found that it's surprisingly insensitive to the amount of regularization applied, however it definitely does warrant further experimentation. Also, I expect that one other distinction vs. image data is much higher correlation between samples in the dataset.

But maybe with 5 million real examples sampled from the distribution CIFAR-10 was sampled from they would in fact see a difference. Maybe the generative model is capturing only a limited slice of the diversity that the ideal model would really see.

It seems like they should have downsampled from an actually large dataset rather than generatively upsampled from a small dataset. Unless I'm missing something?

I think what you're saying is plausible, but I would expect the different models to diverge at different rates in that case. So, for example, if resnet-real and resnet-ideal stayed within 1% and the other models showed a bigger range, I would be more suspicious that the generative model was simply creating a dataset that was easy for some architectures to learn.

That being said, I think it would have been much better if they compared some non-convolutional architectures just as a sanity check

Edit: after I wrote this, I checked, and ViT-b/4 is actually a transformer architecture, not CNN. So they did this! And it stayed very close to the same error range from ideal as the CNNs. I am much more confident now that what they did is fine

I glanced over the paper and it appears that the generative model used for cifar-5m wasn't even trained with a proper train/test split. It was simply trained until the FID on the training set stopped decreasing. That's a pretty good way to overfit a model -- especially on a dataset as small as cifar-10 -- so it's hard to trust that cifar-5m is a decent proxy for the underlying cifar-10 data distribution.

This stood out to me too and puts a big question mark over the whole framework.

Seriously...

What's surprising is that Google has an enormous dataset called JFT where they could have tested this without this confound. Just shrink the images and you can make something cifar-like and something cifar-5m-like

or even just an ablation on Imagenet or some other “large” dataset. Did this paper get accepted because it has five pages of citations and invokes Vapnik in the second sentence?

We have ImageNet experiments in Section 4 of the full paper: https://arxiv.org/abs/2010.08127

You're not ablating anything there. What happens when Train Infinity (Train 150K) doubles in size (to Train Infinity_2 -> 300K)? What happens when you add an unseen class? These are real-world conditions that hamper existing theoretical estimation of the generalization gap-- the "ideal world" always gets larger. In Bengio's group paper (Predicting the Generalization Gap https://arxiv.org/pdf/1810.00113.pdf ) they actually do these sorts of ablations.

Also, you use K (thousands) and $K$ (latex K) interchangeably; it's really hard to decipher is K is a variable or what you mean.

Why would you criticize them so hard for not doing imagenet experiments when they did do them?

This article was promoted by Google's PR blog and the conference is ultra selective (probably excessively selective). Hyped results deserve extra criticism. And no, they didn't do any useful ablation experiments.

I dont know if it is depressing or encouraging that a team of learned guys who get paid mid 6-figures come up with this kind of strategy.

Reply on news.ycombinator.com