Understanding the geometry of deep learning with decision boundary volume

• URL: http://arxiv.org/abs/2603.14768v1
• Date: Mon, 16 Mar 2026 03:02:52 GMT
• Title: Understanding the geometry of deep learning with decision boundary volume
• Abstract summary: We introduce a method to measure the decision boundary of a neural network through local surface volumes.<n>A smaller surface volume is expected to correspond to lower model complexity and better generalisation.<n>We demonstrate that smoother decision boundaries lead to better performance.
• Score: 0.3288086999241324
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: For classification tasks, the performance of a deep neural network is determined by the structure of its decision boundary, whose geometry directly affects essential properties of the model, including accuracy and robustness. Motivated by a classical tube formula due to Weyl, we introduce a method to measure the decision boundary of a neural network through local surface volumes, providing a theoretically justifiable and efficient measure enabling a geometric interpretation of the effectiveness of the model applicable to the high dimensional feature spaces considered in deep learning. A smaller surface volume is expected to correspond to lower model complexity and better generalisation. We verify, on a number of image processing tasks with convolutional architectures that decision boundary volume is inversely proportional to classification accuracy. Meanwhile, the relationship between local surface volume and generalisation for fully connected architecture is observed to be less stable between tasks. Therefore, for network architectures suited to a particular data structure, we demonstrate that smoother decision boundaries lead to better performance, as our intuition would suggest.

Related papers

• SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces [91.71563221166417]
  Implicit neural representations are powerful for geometric modeling, but their practical use is often limited by the high computational cost.<n>We propose an efficient neural implicit geometry representation framework with spatially adaptive network depth.
  arXiv  Detail & Related papers  (2026-04-15T14:14:17Z)
• An accurate flatness measure to estimate the generalization performance of CNN models [2.867517731896504]
  We develop a flatness measure that is both exact and architecturally faithful for a broad and practically relevant class of CNNs.<n>The results suggest that the proposed measure can serve as a tool to assess and compare the generalization of CNN models.
  arXiv  Detail & Related papers  (2026-03-09T23:17:49Z)
• Generalized Factor Neural Network Model for High-dimensional Regression [50.554377879576066]
  We tackle the challenges of modeling high-dimensional data sets with latent low-dimensional structures hidden within complex, non-linear, and noisy relationships.<n>Our approach enables a seamless integration of concepts from non-parametric regression, factor models, and neural networks for high-dimensional regression.
  arXiv  Detail & Related papers  (2025-02-16T23:13:55Z)
• Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
  Task-oriented edge computing addresses this by shifting data analysis to the edge. Existing methods struggle to balance high model performance with low resource consumption. We propose a novel co-design framework to optimize neural network architecture.
  arXiv  Detail & Related papers  (2024-10-29T19:02:54Z)
• Quasi-orthogonality and intrinsic dimensions as measures of learning and generalisation [55.80128181112308]
  We show that dimensionality and quasi-orthogonality of neural networks' feature space may jointly serve as network's performance discriminants. Our findings suggest important relationships between the networks' final performance and properties of their randomly initialised feature spaces.
  arXiv  Detail & Related papers  (2022-03-30T21:47:32Z)
• Adaptive Surface Normal Constraint for Depth Estimation [102.7466374038784]
  We introduce a simple yet effective method, named Adaptive Surface Normal (ASN) constraint, to correlate the depth estimation with geometric consistency. Our method can faithfully reconstruct the 3D geometry and is robust to local shape variations, such as boundaries, sharp corners and noises.
  arXiv  Detail & Related papers  (2021-03-29T10:36:25Z)
• 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)
• Data-driven effective model shows a liquid-like deep learning [2.0711789781518752]
  It remains unknown what the landscape looks like for deep networks of binary synapses. We propose a statistical mechanics framework by directly building a least structured model of the high-dimensional weight space. Our data-driven model thus provides a statistical mechanics insight about why deep learning is unreasonably effective in terms of the high-dimensional weight space.
  arXiv  Detail & Related papers  (2020-07-16T04:02:48Z)
• Dataless Model Selection with the Deep Frame Potential [45.16941644841897]
  We quantify networks by their intrinsic capacity for unique and robust representations. We propose the deep frame potential: a measure of coherence that is approximately related to representation stability but has minimizers that depend only on network structure. We validate its use as a criterion for model selection and demonstrate correlation with generalization error on a variety of common residual and densely connected network architectures.
  arXiv  Detail & Related papers  (2020-03-30T23:27:25Z)
• Local Propagation in Constraint-based Neural Network [77.37829055999238]
  We study a constraint-based representation of neural network architectures. We investigate a simple optimization procedure that is well suited to fulfil the so-called architectural constraints.
  arXiv  Detail & Related papers  (2020-02-18T16:47:38Z)
• A deep learning approach for the computation of curvature in the level-set method [0.0]
  We propose a strategy to estimate the mean curvature of two-dimensional implicit in the level-set method. Our approach is based on fitting feed-forward neural networks to synthetic data sets constructed from circular immersed in uniform grids of various resolutions.
  arXiv  Detail & Related papers  (2020-02-04T00:49:47Z)

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.