Mitigating the Curse of Detail: Scaling Arguments for Feature Learning and Sample Complexity

• URL: http://arxiv.org/abs/2512.04165v3
• Date: Tue, 09 Dec 2025 16:55:27 GMT
• Title: Mitigating the Curse of Detail: Scaling Arguments for Feature Learning and Sample Complexity
• Authors: Noa Rubin, Orit Davidovich, Zohar Ringel,
• Abstract summary: Two pressing topics in the theory of deep learning are the interpretation of feature learning mechanisms and the determination of implicit bias of networks in the rich regime.<n>Here, we propose a powerful route for predicting the data and width scales at which various patterns of feature learning emerge.
• Score: 6.678130184505637
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Two pressing topics in the theory of deep learning are the interpretation of feature learning mechanisms and the determination of implicit bias of networks in the rich regime. Current theories of rich feature learning, often appear in the form of high-dimensional non-linear equations, which require computationally intensive numerical solutions. Given the many details that go into defining a deep learning problem, this complexity is a significant and often unavoidable challenge. Here, we propose a powerful heuristic route for predicting the data and width scales at which various patterns of feature learning emerge. This form of scale analysis is considerably simpler than exact theories and reproduces the scaling exponents of various known results. In addition, we make novel predictions on complex toy architectures, such as three-layer non-linear networks and attention heads, thus extending the scope of first-principle theories of deep learning.

Related papers

• Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation [7.079039376205091]
  We study the supervised learning of a multi-layer perceptron.<n>We focus on the challenging regime where the number of trainable parameters and data are comparable.<n>Despite its simplicity, the Bayesian-optimal setting provides insights on how the depth, non-linearity and finite (proportional) width influence neural networks.
  arXiv  Detail & Related papers  (2025-10-28T16:44:34Z)
• Random Matrix Theory for Deep Learning: Beyond Eigenvalues of Linear Models [51.85815025140659]
  Modern Machine Learning (ML) and Deep Neural Networks (DNNs) often operate on high-dimensional data.<n>In particular, the proportional regime where the data dimension, sample size, and number of model parameters are all large gives rise to novel and sometimes counterintuitive behaviors.<n>This paper extends traditional Random Matrix Theory (RMT) beyond eigenvalue-based analysis of linear models to address the challenges posed by nonlinear ML models.
  arXiv  Detail & Related papers  (2025-06-16T06:54:08Z)
• Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond [61.18736646013446]
  In pursuit of a deeper understanding of its surprising behaviors, we investigate the utility of a simple yet accurate model of a trained neural network. Across three case studies, we illustrate how it can be applied to derive new empirical insights on a diverse range of prominent phenomena.
  arXiv  Detail & Related papers  (2024-10-31T22:54:34Z)
• Foundations and Frontiers of Graph Learning Theory [81.39078977407719]
  Recent advancements in graph learning have revolutionized the way to understand and analyze data with complex structures. Graph Neural Networks (GNNs), i.e. neural network architectures designed for learning graph representations, have become a popular paradigm. This article provides a comprehensive summary of the theoretical foundations and breakthroughs concerning the approximation and learning behaviors intrinsic to prevalent graph learning models.
  arXiv  Detail & Related papers  (2024-07-03T14:07:41Z)
• Applying statistical learning theory to deep learning [21.24637996678039]
  The goal of these lectures is to provide an overview of some of the main questions that arise when attempting to understand deep learning. We discuss implicit bias in the context of benign overfitting. We provide a detailed study of the implicit bias of gradient descent on linear diagonal networks for various regression tasks.
  arXiv  Detail & Related papers  (2023-11-26T20:00:53Z)
• Deep networks for system identification: a Survey [56.34005280792013]
  System identification learns mathematical descriptions of dynamic systems from input-output data. Main aim of the identified model is to predict new data from previous observations. We discuss architectures commonly adopted in the literature, like feedforward, convolutional, and recurrent networks.
  arXiv  Detail & Related papers  (2023-01-30T12:38:31Z)
• An Information-Theoretic Framework for Supervised Learning [22.280001450122175]
  We propose a novel information-theoretic framework with its own notions of regret and sample complexity. We study the sample complexity of learning from data generated by deep neural networks with ReLU activation units. We conclude by corroborating our theoretical results with experimental analysis of random single-hidden-layer neural networks.
  arXiv  Detail & Related papers  (2022-03-01T05:58:28Z)
• Multi-scale Feature Learning Dynamics: Insights for Double Descent [71.91871020059857]
  We study the phenomenon of "double descent" of the generalization error. We find that double descent can be attributed to distinct features being learned at different scales.
  arXiv  Detail & Related papers  (2021-12-06T18:17:08Z)
• The Principles of Deep Learning Theory [19.33681537640272]
  This book develops an effective theory approach to understanding deep neural networks of practical relevance. We explain how these effectively-deep networks learn nontrivial representations from training. We show that the depth-to-width ratio governs the effective model complexity of the ensemble of trained networks.
  arXiv  Detail & Related papers  (2021-06-18T15:00:00Z)
• A neural anisotropic view of underspecification in deep learning [60.119023683371736]
  We show that the way neural networks handle the underspecification of problems is highly dependent on the data representation. Our results highlight that understanding the architectural inductive bias in deep learning is fundamental to address the fairness, robustness, and generalization of these systems.
  arXiv  Detail & Related papers  (2021-04-29T14:31:09Z)
• Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
  We propose a topological perspective to represent a network into a complete graph for analysis. By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner. This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
  arXiv  Detail & Related papers  (2020-08-19T04:53:31Z)
• Structure preserving deep learning [1.2263454117570958]
  deep learning has risen to the foreground as a topic of massive interest. There are multiple challenging mathematical problems involved in applying deep learning. A growing effort to mathematically understand the structure in existing deep learning methods.
  arXiv  Detail & Related papers  (2020-06-05T10:59:09Z)

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.