Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime

• URL: http://arxiv.org/abs/2509.24882v1
• Date: Mon, 29 Sep 2025 14:58:13 GMT
• Title: Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
• Authors: Leonardo Defilippis, Yizhou Xu, Julius Girardin, Emanuele Troiani, Vittorio Erba, Lenka Zdeborová, Bruno Loureiro, Florent Krzakala,
• Abstract summary: We present a systematic analysis of scaling laws for quadratic and diagonal neural networks in the feature learning regime.<n>We derive a detailed phase diagram for the scaling exponents of the excess risk as a function of sample complexity and weight decay.<n>We provide a theoretical validation of recent empirical observations connecting the emergence of power-law tails in the weight spectrum with network generalization performance.
• Score: 34.77547342230355
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural scaling laws underlie many of the recent advances in deep learning, yet their theoretical understanding remains largely confined to linear models. In this work, we present a systematic analysis of scaling laws for quadratic and diagonal neural networks in the feature learning regime. Leveraging connections with matrix compressed sensing and LASSO, we derive a detailed phase diagram for the scaling exponents of the excess risk as a function of sample complexity and weight decay. This analysis uncovers crossovers between distinct scaling regimes and plateau behaviors, mirroring phenomena widely reported in the empirical neural scaling literature. Furthermore, we establish a precise link between these regimes and the spectral properties of the trained network weights, which we characterize in detail. As a consequence, we provide a theoretical validation of recent empirical observations connecting the emergence of power-law tails in the weight spectrum with network generalization performance, yielding an interpretation from first principles.

Related papers

• Models of Heavy-Tailed Mechanistic Universality [62.107333654304014]
  We propose a family of random matrix models to explore attributes that give rise to heavy-tailed behavior in trained neural networks.<n>Under this model, spectral densities with power laws on tails arise through a combination of three independent factors.<n> Implications of our model on other appearances of heavy tails, including neural scaling laws, trajectories, and the five-plus-one phases of neural network training, are discussed.
  arXiv  Detail & Related papers  (2025-06-04T00:55:01Z)
• Implicit bias produces neural scaling laws in learning curves, from perceptrons to deep networks [12.108234998867337]
  We identify two novel textitdynamical scaling laws that govern how performance evolves as function of different norm-based complexity measures.<n>Our findings are consistent across CNNs, ResNets, and Vision Transformers trained on MNIST, CIFAR-10 and CIFAR-100.<n>We provide analytical support using a single-layer perceptron trained with logistic loss, where we derive the new dynamical scaling laws, and we explain them through the implicit bias induced by gradient-based training.
  arXiv  Detail & Related papers  (2025-05-19T15:13:36Z)
• Theoretical characterisation of the Gauss-Newton conditioning in Neural Networks [5.851101657703105]
  We take a first step towards theoretically characterizing the conditioning of the Gauss-Newton (GN) matrix in neural networks.<n>We establish tight bounds on the condition number of the GN in deep linear networks of arbitrary depth and width.<n>We expand the analysis to further architectural components, such as residual connections and convolutional layers.
  arXiv  Detail & Related papers  (2024-11-04T14:56:48Z)
• Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra [0.0]
  Neural scaling laws describe how the performance of deep neural networks scales with key factors such as training data size, model complexity, and training time. We employ techniques from statistical mechanics to analyze one-pass gradient descent within a student-teacher framework.
  arXiv  Detail & Related papers  (2024-10-11T17:21:42Z)
• Approaching Deep Learning through the Spectral Dynamics of Weights [41.948042468042374]
  spectral dynamics of weights -- the behavior of singular values and vectors during optimization -- to clarify and unify several phenomena in deep learning. We identify a consistent bias in optimization across various experiments, from small-scale grokking'' to large-scale tasks like image classification with ConvNets, image generation with UNets, speech recognition with LSTMs, and language modeling with Transformers.
  arXiv  Detail & Related papers  (2024-08-21T17:48:01Z)
• Generalization of Scaled Deep ResNets in the Mean-Field Regime [55.77054255101667]
  We investigate emphscaled ResNet in the limit of infinitely deep and wide neural networks. Our results offer new insights into the generalization ability of deep ResNet beyond the lazy training regime.
  arXiv  Detail & Related papers  (2024-03-14T21:48:00Z)
• Universal Scaling Laws of Absorbing Phase Transitions in Artificial Deep Neural Networks [0.8932296777085644]
  Conventional artificial deep neural networks operating near the phase boundary of the signal propagation dynamics, also known as the edge of chaos, exhibit universal scaling laws of absorbing phase transitions.<n>We exploit the fully deterministic nature of the propagation dynamics to elucidate an analogy between a signal collapse in the neural networks and an absorbing state.
  arXiv  Detail & Related papers  (2023-07-05T13:39:02Z)
• Gradient Descent in Neural Networks as Sequential Learning in RKBS [63.011641517977644]
  We construct an exact power-series representation of the neural network in a finite neighborhood of the initial weights. We prove that, regardless of width, the training sequence produced by gradient descent can be exactly replicated by regularized sequential learning.
  arXiv  Detail & Related papers  (2023-02-01T03:18:07Z)
• Formalizing Generalization and Robustness of Neural Networks to Weight Perturbations [58.731070632586594]
  We provide the first formal analysis for feed-forward neural networks with non-negative monotone activation functions against weight perturbations. We also design a new theory-driven loss function for training generalizable and robust neural networks against weight perturbations.
  arXiv  Detail & Related papers  (2021-03-03T06:17:03Z)
• Kernel and Rich Regimes in Overparametrized Models [69.40899443842443]
  We show that gradient descent on overparametrized multilayer networks can induce rich implicit biases that are not RKHS norms. We also demonstrate this transition empirically for more complex matrix factorization models and multilayer non-linear networks.
  arXiv  Detail & Related papers  (2020-02-20T15:43:02Z)
• Understanding Generalization in Deep Learning via Tensor Methods [53.808840694241]
  We advance the understanding of the relations between the network's architecture and its generalizability from the compression perspective. We propose a series of intuitive, data-dependent and easily-measurable properties that tightly characterize the compressibility and generalizability of neural networks.
  arXiv  Detail & Related papers  (2020-01-14T22:26:57Z)

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.