Preconditioned gradient descent mitigates spectral bias and reduces grokking delays by enabling uniform parameter space exploration in the NTK regime, confirming grokking as a transition to the rich regime.
Exact, tractable gauss-newton optimization in deep reversible architectures reveal poor generalization.arXiv preprint arXiv:2411.07979,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On the Convergence Behavior of Preconditioned Gradient Descent Toward the Rich Learning Regime
Preconditioned gradient descent mitigates spectral bias and reduces grokking delays by enabling uniform parameter space exploration in the NTK regime, confirming grokking as a transition to the rich regime.