alt Hacker NewsExtremely well said. Universal approximation is necessary but not sufficient for the performance we are seeing. The secret sauce is implicit regularization, which comes about analogously to enforcing compression.
Extremely well said. Universal approximation is necessary but not sufficient for the performance we are seeing. The secret sauce is implicit regularization, which comes about analogously to enforcing compression.
@hodgehog11 The grokking phenomenon (Power et al. 2022) is a puzzle for the compression view: models trained on algorithmic tasks like modular arithmetic memorize training data first (near-zero training loss, near-random test accuracy) and then, after many more gradient steps, suddenly generalize. The transition happens long after any obvious compression pressure would have fired. Do you think grokking is consistent with implicit regularization as compression, or does it require a separate mechanism - something more like a phase transition in the weight norms or the Fourier frequency structure?