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

• URL: http://arxiv.org/abs/2505.22491v2
• Date: Sat, 25 Oct 2025 11:34:31 GMT
• Title: On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling
• Authors: Moritz Haas, Sebastian Bordt, Ulrike von Luxburg, Leena Chennuru Vankadara,
• Abstract summary: We show that optimal learning rates decay slower than theoretically predicted and networks exhibit both stable training and non-trivial feature learning, even at very large widths.<n>In particular, we show that under cross-entropy (CE) loss, the unstable regime comprises two distinct sub-regimes: a catastrophically unstable regime and a more benign controlled divergence regime.<n>Our empirical evidence suggests that width-scaling considerations are surprisingly useful for predicting empirically maximal stable learning rate exponents.
• Score: 15.769249369390884
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Scaling limits, such as infinite-width limits, serve as promising theoretical tools to study large-scale models. However, it is widely believed that existing infinite-width theory does not faithfully explain the behavior of practical networks, especially those trained in standard parameterization (SP) meaning He initialization with a global learning rate. For instance, existing theory for SP predicts instability at large learning rates and vanishing feature learning at stable ones. In practice, however, optimal learning rates decay slower than theoretically predicted and networks exhibit both stable training and non-trivial feature learning, even at very large widths. Here, we show that this discrepancy is not fully explained by finite-width phenomena. Instead, we find a resolution through a finer-grained analysis of the regime previously considered unstable and therefore uninteresting. In particular, we show that, under cross-entropy (CE) loss, the unstable regime comprises two distinct sub-regimes: a catastrophically unstable regime and a more benign controlled divergence regime, where logits diverge but gradients and activations remain stable. Moreover, under large learning rates at the edge of the controlled divergence regime, there exists a well-defined infinite width limit where features continue to evolve in all the hidden layers. In experiments across optimizers, architectures, and data modalities, 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 maximal stable learning rate exponents which provide useful guidance on optimal learning rate exponents. Finally, our analysis clarifies the effectiveness and limitations of recently proposed layerwise learning rate scaling for standard initialization.

Related papers

• Understanding Scaling Laws in Deep Neural Networks via Feature Learning Dynamics [9.885471525709113]
  We show that scaling laws describe what success looks like but not when and why scaling succeeds or fails.<n>A central obstacle is the lack of a rigorous understanding of feature learning at large depth.
  arXiv  Detail & Related papers  (2025-12-24T09:39:04Z)
• Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks [100.13335639780415]
  Scaling laws often follow the power-law and proposed several variants of power-law functions to predict the scaling behavior at larger scales.<n>Existing methods mostly rely on point estimation and do not quantify uncertainty, which is crucial for real-world applications.<n>In this work, we explore a Bayesian framework based on Prior-data Fitted Networks (PFNs) for neural scaling law extrapolation.
  arXiv  Detail & Related papers  (2025-05-29T03:19:17Z)
• CLUE: Neural Networks Calibration via Learning Uncertainty-Error alignment [7.702016079410588]
  We introduce CLUE (Calibration via Learning Uncertainty-Error Alignment), a novel approach that aligns predicted uncertainty with observed error during training.<n>We show that CLUE achieves superior calibration quality and competitive predictive performance with respect to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-05-28T19:23:47Z)
• Precise gradient descent training dynamics for finite-width multi-layer neural networks [8.057006406834466]
  We provide the first precise distributional characterization of gradient descent iterates for general multi-layer neural networks.<n>Our non-asymptotic state evolution theory captures Gaussian fluctuations in first-layer weights and concentration in deeper-layer weights.
  arXiv  Detail & Related papers  (2025-05-08T02:19:39Z)
• Normalization and effective learning rates in reinforcement learning [52.59508428613934]
  Normalization layers have recently experienced a renaissance in the deep reinforcement learning and continual learning literature. We show that normalization brings with it a subtle but important side effect: an equivalence between growth in the norm of the network parameters and decay in the effective learning rate. We propose to make the learning rate schedule explicit with a simple re- parameterization which we call Normalize-and-Project.
  arXiv  Detail & Related papers  (2024-07-01T20:58:01Z)
• Preventing Collapse in Contrastive Learning with Orthonormal Prototypes (CLOP) [0.0]
  CLOP is a novel semi-supervised loss function designed to prevent neural collapse by promoting the formation of linear subspaces among class embeddings. We show that CLOP enhances performance, providing greater stability across different learning rates and batch sizes.
  arXiv  Detail & Related papers  (2024-03-27T15:48:16Z)
• Variation Due to Regularization Tractably Recovers Bayesian Deep Learning [44.16006844888796]
  We propose an uncertainty quantification method for large networks based on variation due to regularization.<n>We show that regularization variation (RegVar) provides rigorous uncertainty estimates that, in the infinitesimal limit, exactly recover the Laplace approximation in Bayesian deep learning.<n>Our experiments across multiple datasets show that RegVar not only identifies uncertain predictions effectively but also provides insights into the stability of learned representations.
  arXiv  Detail & Related papers  (2024-03-15T20:47:39Z)
• Neural Network Approximation for Pessimistic Offline Reinforcement Learning [17.756108291816908]
  We present a non-asymptotic estimation error of pessimistic offline RL using general neural network approximation. Our result shows that the estimation error consists of two parts: the first converges to zero at a desired rate on the sample size with partially controllable concentrability, and the second becomes negligible if the residual constraint is tight.
  arXiv  Detail & Related papers  (2023-12-19T05:17:27Z)
• On the Dynamics Under the Unhinged Loss and Beyond [104.49565602940699]
  We introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze closed-form dynamics. The unhinged loss allows for considering more practical techniques, such as time-vary learning rates and feature normalization.
  arXiv  Detail & Related papers  (2023-12-13T02:11:07Z)
• Boosted Control Functions: Distribution generalization and invariance in confounded models [10.503777692702952]
  We introduce a strong notion of invariance that allows for distribution generalization even in the presence of nonlinear, non-identifiable structural functions.<n>We propose the ControlTwicing algorithm to estimate the Boosted Control Function (BCF) using flexible machine-learning techniques.
  arXiv  Detail & Related papers  (2023-10-09T15:43:46Z)
• On Double Descent in Reinforcement Learning with LSTD and Random Features [1.5873758872998507]
  Temporal Difference (TD) algorithms are widely used in Deep Reinforcement Learning (RL) We present a theoretical analysis of the influence of network size and $l$-regularization on performance. We observe a double descent phenomenon, i.e., a sudden drop in performance around the parameter/state ratio of one.
  arXiv  Detail & Related papers  (2023-10-09T08:33:22Z)
• Feature-Learning Networks Are Consistent Across Widths At Realistic Scales [72.27228085606147]
  We study the effect of width on the dynamics of feature-learning neural networks across a variety of architectures and datasets. Early in training, wide neural networks trained on online data have not only identical loss curves but also agree in their point-wise test predictions throughout training. We observe, however, that ensembles of narrower networks perform worse than a single wide network.
  arXiv  Detail & Related papers  (2023-05-28T17:09:32Z)
• Theoretical Characterization of the Generalization Performance of Overfitted Meta-Learning [70.52689048213398]
  This paper studies the performance of overfitted meta-learning under a linear regression model with Gaussian features. We find new and interesting properties that do not exist in single-task linear regression. Our analysis suggests that benign overfitting is more significant and easier to observe when the noise and the diversity/fluctuation of the ground truth of each training task are large.
  arXiv  Detail & Related papers  (2023-04-09T20:36:13Z)
• Uncertainty Estimation by Fisher Information-based Evidential Deep Learning [61.94125052118442]
  Uncertainty estimation is a key factor that makes deep learning reliable in practical applications. We propose a novel method, Fisher Information-based Evidential Deep Learning ($mathcalI$-EDL) In particular, we introduce Fisher Information Matrix (FIM) to measure the informativeness of evidence carried by each sample, according to which we can dynamically reweight the objective loss terms to make the network more focused on the representation learning of uncertain classes.
  arXiv  Detail & Related papers  (2023-03-03T16:12:59Z)
• Modeling Uncertain Feature Representation for Domain Generalization [49.129544670700525]
  We show that our method consistently improves the network generalization ability on multiple vision tasks. Our methods are simple yet effective and can be readily integrated into networks without additional trainable parameters or loss constraints.
  arXiv  Detail & Related papers  (2023-01-16T14:25:02Z)
• A PDE-based Explanation of Extreme Numerical Sensitivities and Edge of Stability in Training Neural Networks [12.355137704908042]
  We show restrained numerical instabilities in current training practices of deep networks with gradient descent (SGD) We do this by presenting a theoretical framework using numerical analysis of partial differential equations (PDE), and analyzing the gradient descent PDE of convolutional neural networks (CNNs) We show this is a consequence of the non-linear PDE associated with the descent of the CNN, whose local linearization changes when over-driving the step size of the discretization resulting in a stabilizing effect.
  arXiv  Detail & Related papers  (2022-06-04T14:54:05Z)
• Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate [105.62979485062756]
  This paper attempts to characterize the particular regularization effect of SGD in the moderate learning rate regime. We show that SGD converges along the large eigenvalue directions of the data matrix, while GD goes after the small eigenvalue directions.
  arXiv  Detail & Related papers  (2020-11-04T21:07:52Z)
• Revisiting Initialization of Neural Networks [72.24615341588846]
  We propose a rigorous estimation of the global curvature of weights across layers by approximating and controlling the norm of their Hessian matrix. Our experiments on Word2Vec and the MNIST/CIFAR image classification tasks confirm that tracking the Hessian norm is a useful diagnostic tool.
  arXiv  Detail & Related papers  (2020-04-20T18:12:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.