On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling

The dominant paradigm for training large-scale vision and language models is He initialization and a single global learning rate (\textit{standard parameterization}, SP). Despite its practical success, standard parametrization remains poorly understood from a theoretical perspective: Existing infinite-width theory would predict instability under large learning rates and vanishing feature learning under stable learning rates. However, empirically optimal learning rates consistently decay much slower than theoretically predicted. By carefully studying neural network training dynamics, we demonstrate that this discrepancy is not fully explained by finite-width phenomena such as catapult effects or a lack of alignment between weights and incoming activations. We instead show that the apparent contradiction can be fundamentally resolved by taking the loss function into account: In contrast to Mean Squared Error (MSE) loss, we prove that under cross-entropy (CE) loss, an intermediate \textit{controlled divergence} regime emerges, where logits diverge but loss, gradients, and activations remain stable. Stable training under large learning rates enables persistent feature evolution at scale in all hidden layers, which is crucial for the practical success of SP. In experiments across optimizers (SGD, Adam), architectures (MLPs, GPT) and data modalities (vision, language), we validate that neural networks operate in this controlled divergence regime under CE loss but not under MSE loss. Our empirical evidence suggests that width-scaling considerations are surprisingly useful for predicting empirically optimal learning rate exponents. Finally, our analysis clarifies the effectiveness and limitations of recently proposed layerwise learning rate scalings for standard initialization.

@article{haas2025_2505.22491,
  title={ On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling },
  author={ Moritz Haas and Sebastian Bordt and Ulrike von Luxburg and Leena Chennuru Vankadara },
  journal={arXiv preprint arXiv:2505.22491},
  year={ 2025 }
}