Pointwise Generalization in Deep Neural Networks

• URL: http://arxiv.org/abs/2605.18598v1
• Date: Mon, 18 May 2026 16:09:06 GMT
• Title: Pointwise Generalization in Deep Neural Networks
• Abstract summary: We identify the structural properties and mathematical principles that explain the tractability of deep networks.<n>We show that deep networks are mathematically tractable in practical regimes and that their generalization is sharply explained by pointwise, feature-spectrum-aware complexity.
• Score: 24.565019622696664
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We address the fundamental question of why deep neural networks generalize by establishing a pointwise generalization theory for fully connected networks. This framework resolves long-standing barriers to characterizing the rich nonlinear feature-learning regime and builds a new statistical foundation for representation learning. For each trained model, we characterize the hypothesis via a pointwise Riemannian Dimension, derived from the eigenvalues of the learned feature representations across layers. This establishes a principled framework for deriving hypothesis-dependent, representation-aware generalization bounds. These bounds offer a systematic upgrade over approaches based on model size, products of norms, and infinite-width linearizations, yielding guarantees that are orders of magnitude tighter in both theory and experiment. Analytically, we identify the structural properties and mathematical principles that explain the tractability of deep networks. Empirically, the pointwise Riemannian Dimension exhibits substantial feature compression, decreases with increased over-parameterization, and captures the implicit bias of optimizers. Taken together, our results indicate that deep networks are mathematically tractable in practical regimes and that their generalization is sharply explained by pointwise, feature-spectrum-aware complexity.

Related papers

• Approximation Theory for Neural Networks: Old and New [1.6300219183960216]
  Universal approximations provide a mathematical explanation for the expressive power of neural networks.<n>We review classical density results for single-hidden-layer networks, as well as quantitative bounds that relate approximation error to network size.<n>Recent developments on Kolmogorov--Arnold Networks (KANs) offer an alternative architectural paradigm.
  arXiv  Detail & Related papers  (2026-05-20T17:42:34Z)
• Axiomatizing Neural Networks via Pursuit of Subspaces [18.584665304905897]
  We introduce the Pursuit of Subspaces (PoS) hypothesis, an axiomatic framework that formulates neural network behavior through a set of geometrics.<n>We show that this framework yields geometric explanations for fundamental questions in deep learning, including representation structure, architectural mechanisms, and generalization behavior.
  arXiv  Detail & Related papers  (2026-05-19T22:12:58Z)
• The Inductive Bias of Convolutional Neural Networks: Locality and Weight Sharing Reshape Implicit Regularization [57.37943479039033]
  We study how architectural inductive bias reshapes the implicit regularization induced by the edge-of-stability phenomenon in gradient descent.<n>We show that locality and weight sharing fundamentally change this picture.
  arXiv  Detail & Related papers  (2026-03-05T04:50:51Z)
• Conjugate Learning Theory: Uncovering the Mechanisms of Trainability and Generalization in Deep Neural Networks [0.0]
  We develop a conjugate learning theoretical framework based on convex conjugate duality to characterize this learnability property.<n>We demonstrate that training deep neural networks (DNNs) with mini-batch descent (SGD) achieves global optima of empirical risk.<n>We derive deterministic and probabilistic bounds on generalization error based on conditional generalized entropy measures.
  arXiv  Detail & Related papers  (2026-02-18T04:26:55Z)
• Towards A Unified PAC-Bayesian Framework for Norm-based Generalization Bounds [63.47271262149291]
  We propose a unified framework for PAC-Bayesian norm-based generalization.<n>The key to our approach is a sensitivity matrix that quantifies the network outputs with respect to structured weight perturbations.<n>We derive a family of generalization bounds that recover several existing PAC-Bayesian results as special cases.
  arXiv  Detail & Related papers  (2026-01-13T00:42:22Z)
• On residual network depth [7.233401307469166]
  We show that increasing network depth is mathematically equivalent to expanding the size of an implicit ensemble.<n>Our work offers the first explanation derived from the network's inherent functional structure.<n>We further show that this scaling acts as a capacity controls that also implicitly regularizes the model's complexity.
  arXiv  Detail & Related papers  (2025-10-03T19:48:48Z)
• How You Start Matters for Generalization [26.74340246715699]
  We show that the generalization of neural networks is heavily tied to their initializes. We make a case against the controversial flat-minima conjecture.
  arXiv  Detail & Related papers  (2022-06-17T05:30:56Z)
• 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)
• Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics [50.83356836818667]
  We introduce a new theoretical framework to analyze deep learning optimization with connection to its generalization error. Existing frameworks such as mean field theory and neural tangent kernel theory for neural network optimization analysis typically require taking limit of infinite width of the network to show its global convergence.
  arXiv  Detail & Related papers  (2020-07-11T18:19:50Z)
• 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.