Mitigating the Curse of Dimensionality in Uniform Convergence of Deep Neural Networks via Smooth Activations

• URL: http://arxiv.org/abs/2606.05599v1
• Date: Thu, 04 Jun 2026 02:24:50 GMT
• Title: Mitigating the Curse of Dimensionality in Uniform Convergence of Deep Neural Networks via Smooth Activations
• Abstract summary: This paper establishes a theoretical framework for the uniform convergence of smoothly activated deep neural network (DNN) estimators.<n>We prove that smooth DNNs can mitigate the curse of dimensionality in uniform convergence by adaptively exploiting the low-dimensional hierarchical composition structure of the target function.
• Score: 13.626248090879235
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper establishes a theoretical framework for the uniform convergence of smoothly activated deep neural network (DNN) estimators. While standard ReLU networks achieve minimax-optimal rates in the $L^2(P)$ norm for various nonparametric regression tasks, we establish a theoretical lower bound demonstrating that least-squares ReLU estimators can suffer from the curse of dimensionality in their uniform convergence behavior. Motivated by the need for reliable uniform guarantees in downstream tasks requiring worst-case reliability, we address this limitation by analyzing smoothly activated DNNs (smooth DNNs), encompassing both feedforward and residual structures. We establish novel pseudo-dimension bounds, non-asymptotic approximation guarantees, and Hölder-norm bounds for the approximators of these models. Leveraging these results, we derive non-asymptotic uniform convergence rates for smooth DNN estimators across multiple statistical contexts, including Huber, least-squares, quantile, and logistic regression. We prove that smooth DNNs can mitigate the {curse of dimensionality} in uniform convergence by adaptively exploiting the low-dimensional hierarchical composition structure of the target function. Supported by both simulation studies and a real-world application, our results position smooth DNNs as a theoretically grounded and practically viable alternative to ReLU networks for statistical learning tasks requiring uniform guarantees.

Related papers

• Reducing ANN-SNN Conversion Error via Residual Membrane Potential Alignment [52.910770415431244]
  Spiking Neural Networks (SNNs) serve as core architectures for neuromorphic computing.<n>ANN-SNN conversion circumvents issues by reusing well-trained ANN weights for low-latency, energy-efficient inference.<n>Existing conversion schemes suffer from severe accuracy drops at small timesteps, large inference delays and cumulative quantization errors.
  arXiv  Detail & Related papers  (2026-08-14T04:46:03Z)
• Pruning Deep Neural Networks via a Combination of the Marchenko-Pastur Distribution and Regularization [0.18641315013048293]
  Vision Transformers (ViTs) have emerged as a powerful class of models in the field of deep learning for image classification.<n>We propose a novel Random Matrix Theory (RMT)-based method for pruning pre-trained DNNs, based on the sparsification of weights and singular vectors.<n>We demonstrate that our RMT-based pruning can be used to reduce the number of parameters of ViT models by 30-50% with less than 1% loss in accuracy.
  arXiv  Detail & Related papers  (2025-03-02T05:25:20Z)
• Fréchet Cumulative Covariance Net for Deep Nonlinear Sufficient Dimension Reduction with Random Objects [22.156257535146004]
  We introduce a new statistical dependence measure termed Fr'echet Cumulative Covariance (FCCov) and develop a novel nonlinear SDR framework based on FCCov.<n>Our approach is not only applicable to complex non-Euclidean data, but also exhibits robustness against outliers.<n>We prove that our method with squared Frobenius norm regularization achieves unbiasedness at the $sigma$-field level.
  arXiv  Detail & Related papers  (2025-02-21T10:55:50Z)
• Optimization Guarantees of Unfolded ISTA and ADMM Networks With Smooth Soft-Thresholding [57.71603937699949]
  We study optimization guarantees, i.e., achieving near-zero training loss with the increase in the number of learning epochs. We show that the threshold on the number of training samples increases with the increase in the network width.
  arXiv  Detail & Related papers  (2023-09-12T13:03:47Z)
• Benign Overfitting in Deep Neural Networks under Lazy Training [72.28294823115502]
  We show that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification. Our results indicate that interpolating with smoother functions leads to better generalization.
  arXiv  Detail & Related papers  (2023-05-30T19:37:44Z)
• Generalization Error Bounds for Deep Neural Networks Trained by SGD [3.148524502470734]
  Generalization error bounds for deep trained by gradient descent (SGD) are derived. The bounds explicitly depend on the loss along the training trajectory. Results show that our bounds are non-vacuous and robust with the change of neural networks and network hypers.
  arXiv  Detail & Related papers  (2022-06-07T13:46:10Z)
• SymNMF-Net for The Symmetric NMF Problem [62.44067422984995]
  We propose a neural network called SymNMF-Net for the Symmetric NMF problem. We show that the inference of each block corresponds to a single iteration of the optimization. Empirical results on real-world datasets demonstrate the superiority of our SymNMF-Net.
  arXiv  Detail & Related papers  (2022-05-26T08:17:39Z)
• Hybrid ISTA: Unfolding ISTA With Convergence Guarantees Using Free-Form Deep Neural Networks [50.193061099112626]
  It is promising to solve linear inverse problems by unfolding iterative algorithms as deep neural networks (DNNs) with learnable parameters. Existing ISTA-based unfolded algorithms restrict the network architectures for iterative updates with the partial weight coupling structure to guarantee convergence. This paper is the first to provide a convergence-provable framework that enables free-form DNNs in ISTA-based unfolded algorithms.
  arXiv  Detail & Related papers  (2022-04-25T13:17:57Z)
• Comparative Analysis of Interval Reachability for Robust Implicit and Feedforward Neural Networks [64.23331120621118]
  We use interval reachability analysis to obtain robustness guarantees for implicit neural networks (INNs) INNs are a class of implicit learning models that use implicit equations as layers. We show that our approach performs at least as well as, and generally better than, applying state-of-the-art interval bound propagation methods to INNs.
  arXiv  Detail & Related papers  (2022-04-01T03:31:27Z)
• Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks [54.27962244835622]
  This paper proposes a new mean-field framework for over- parameterized deep neural networks (DNNs) In this framework, a DNN is represented by probability measures and functions over its features in the continuous limit. We illustrate the framework via the standard DNN and the Residual Network (Res-Net) architectures.
  arXiv  Detail & Related papers  (2020-07-03T01:37:16Z)
• Nonconvex sparse regularization for deep neural networks and its optimality [1.9798034349981162]
  Deep neural network (DNN) estimators can attain optimal convergence rates for regression and classification problems. We propose a novel penalized estimation method for sparse DNNs. We prove that the sparse-penalized estimator can adaptively attain minimax convergence rates for various nonparametric regression problems.
  arXiv  Detail & Related papers  (2020-03-26T07:15:28Z)

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.