free AT doesn‘t work in SVHN about understanding-fast-adv-training

[max-andr]

Hi,

Thanks for the interest in our paper.

As far as I can see, you want to train a model using the approach from "Adversarial training for free". As shown in FIg. 8 (left), we didn't experience any problem training it even when replicated over 5 random seeds.

Did you modify the provided code in some way? Based on my experience, the warmup of the epsilon is quite important on SVHN to prevent the convergence to the most popular class (which leads to 23% accuracy or so):
https://github.com/tml-epfl/understanding-fast-adv-training/blob/master/train.py#L132
Do you use it? Maybe as a sanity check, you can also try to increase it a bit, say, to 10 epochs instead of 5 and see whether it helps. Although in my experiments, it was working well even with 5 warmup epochs.

Best,
Maksym

[max-andr]

Closing it for now. In case you have further questions, feel free to reopen.