Universal Approximation Constraints of Narrow ResNets: The Tunnel Effect

• URL: http://arxiv.org/abs/2603.28591v1
• Date: Mon, 30 Mar 2026 15:37:51 GMT
• Title: Universal Approximation Constraints of Narrow ResNets: The Tunnel Effect
• Abstract summary: We analyze the universal approximation constraints of narrow Residual Neural Networks (ResNets)<n>For deep neural networks without input space augmentation, a central constraint is the inability to represent critical points of the input-output map.<n>We prove that this has global consequences for target function approximations and show that the manifestation of this defect is typically a shift of the critical point to infinity.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We analyze the universal approximation constraints of narrow Residual Neural Networks (ResNets) both theoretically and numerically. For deep neural networks without input space augmentation, a central constraint is the inability to represent critical points of the input-output map. We prove that this has global consequences for target function approximations and show that the manifestation of this defect is typically a shift of the critical point to infinity, which we call the ``tunnel effect'' in the context of classification tasks. While ResNets offer greater expressivity than standard multilayer perceptrons (MLPs), their capability strongly depends on the signal ratio between the skip and residual channels. We establish quantitative approximation bounds for both the residual-dominant (close to MLP) and skip-dominant (close to neural ODE) regimes. These estimates depend explicitly on the channel ratio and uniform network weight bounds. Low-dimensional examples further provide a detailed analysis of the different ResNet regimes and how architecture-target incompatibility influences the approximation error.

Related papers

• Dense Neural Networks are not Universal Approximators [53.27010448621372]
  We show that dense neural networks do not possess universality of arbitrary continuous functions.<n>We consider ReLU neural networks subject to natural constraints on weights and input and output dimensions.
  arXiv  Detail & Related papers  (2026-02-07T16:52:38Z)
• Learning Wireless Interference Patterns: Decoupled GNN for Throughput Prediction in Heterogeneous Multi-Hop p-CSMA Networks [4.303580795892996]
  Decoupled Graph Convolutional Network (D-GCN) is a novel architecture that explicitly separates processing of a node's own transmission probability from neighbor interference effects.<n>D-GCN attains 3.3% NMAE, outperforms strong baselines, remains tractable even when exact analytical methods become computationally infeasible.
  arXiv  Detail & Related papers  (2025-10-15T22:13:59Z)
• Covering Numbers for Deep ReLU Networks with Applications to Function Approximation and Nonparametric Regression [4.297070083645049]
  We develop tight (up to a multiplicative constant) lower and upper bounds on the covering numbers of fully-connected networks. Thanks to the tightness of the bounds, a fundamental understanding of the impact of sparsity, quantization, bounded vs. unbounded weights, and network output truncation can be developed.
  arXiv  Detail & Related papers  (2024-10-08T21:23:14Z)
• Information-Theoretic Generalization Bounds for Deep Neural Networks [20.015357820733406]
  Deep neural networks (DNNs) exhibit an exceptional capacity for generalization in practical applications.<n>This work aims to capture the effect and benefits of depth for supervised learning via information-theoretic generalization bounds.
  arXiv  Detail & Related papers  (2024-04-04T03:20:35Z)
• 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)
• Field theory for optimal signal propagation in ResNets [3.0040661953201475]
  Residual networks have significantly better trainability and performance than feed-forward networks at large depth.<n>Previous works found that adding a scaling parameter for the residual branch further improves generalization performance.<n>We derive a systematic finite-size field theory for residual networks to study signal propagation and its dependence on the scaling for the residual branch.
  arXiv  Detail & Related papers  (2023-05-12T18:14:21Z)
• On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias [50.84569563188485]
  We show that gradient flow converges in direction when labels are determined by the sign of a target network with $r$ neurons. Our result may already hold for mild over- parameterization, where the width is $tildemathcalO(r)$ and independent of the sample size.
  arXiv  Detail & Related papers  (2022-05-18T16:57:10Z)
• On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks [91.3755431537592]
  We study how random pruning of the weights affects a neural network's neural kernel (NTK) In particular, this work establishes an equivalence of the NTKs between a fully-connected neural network and its randomly pruned version.
  arXiv  Detail & Related papers  (2022-03-27T15:22:19Z)
• Phenomenology of Double Descent in Finite-Width Neural Networks [29.119232922018732]
  Double descent delineates the behaviour of models depending on the regime they belong to. We use influence functions to derive suitable expressions of the population loss and its lower bound. Building on our analysis, we investigate how the loss function affects double descent.
  arXiv  Detail & Related papers  (2022-03-14T17:39:49Z)
• Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks [83.58049517083138]
  We consider a two-layer ReLU network trained via gradient descent. We show that SGD is biased towards a simple solution. We also provide empirical evidence that knots at locations distinct from the data points might occur.
  arXiv  Detail & Related papers  (2021-11-03T15:14:20Z)
• Limiting fluctuation and trajectorial stability of multilayer neural networks with mean field training [3.553493344868413]
  We study the fluctuation in the case of multilayer networks at any network depth. We demonstrate through the framework the complex interaction among neurons in this second-order MF limit. A limit theorem is proven to relate this limit to the fluctuation of large-width networks.
  arXiv  Detail & Related papers  (2021-10-29T17:58:09Z)
• Channel-Wise Early Stopping without a Validation Set via NNK Polytope Interpolation [36.479195100553085]
  Convolutional neural networks (ConvNets) comprise high-dimensional feature spaces formed by the aggregation of multiple channels. We present channel-wise DeepNNK, a novel generalization estimate based on non-dimensional kernel regression (NNK) graphs.
  arXiv  Detail & Related papers  (2021-07-27T17:33:30Z)
• 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)
• On Random Kernels of Residual Architectures [93.94469470368988]
  We derive finite width and depth corrections for the Neural Tangent Kernel (NTK) of ResNets and DenseNets. Our findings show that in ResNets, convergence to the NTK may occur when depth and width simultaneously tend to infinity. In DenseNets, however, convergence of the NTK to its limit as the width tends to infinity is guaranteed.
  arXiv  Detail & Related papers  (2020-01-28T16:47:53Z)

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.