Discussion about this post

User's avatar
Daniel Popescu's avatar

This article comes at the perfect time. Leamer's metaphor is truely spot-on for ML. I wonder if these 'sins' aren't often just pragmatic solutions pushing theory forward.

Expand full comment
Raj Movva's avatar

I really like the ImageNet generalization paper, ofc. I think it's interesting that the models have their ranks preserved from S to S', ie the adaptivity gap is small. I think the discussion in the Sec 5.1 "Limited Model Class" paragraph makes sense. But to the extent that you can train the *same architecture* with different random seeds and get different accuracies, and then pick the best random seed based on S, would those gains also generalize to S'?

Expand full comment
3 more comments...

No posts