The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers · HackerPapers discussions

The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers — mentioned by preetum

Sun, 21 Mar 2021 14:37:37 GMT

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

Paper and discussion history. A mention is not an endorsement.

The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers — mentioned by preetum

Sun, 21 Mar 2021 14:36:07 GMT

This is the exact comparison we make in the paper. We have subsampled ImageNet experiments as well; see Figure 3 in the full paper: https://arxiv.org/abs/2010.08127

Paper and discussion history. A mention is not an endorsement.

The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers — mentioned by preetum

Sun, 21 Mar 2021 14:34:34 GMT

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".

Paper and discussion history. A mention is not an endorsement.