cs.LGNov 18, 2026

The geometry of neural network decision boundaries

Authors: Dylan M Paiton, David L Schultheiss, Matthias Kümmerer, Zac Cranko, Matthias Bethge

Organizations: University of Tübingen

Abstract

Artificial neural networks (ANNs) are built using well-understood mathematical operations, yet their complex nature poses significant challenges to intuitively understanding their decision-making processes. This work introduces a method for visualizing and measuring ANN decision boundary geometry directly in the high-dimensional input space, avoiding distortions found with traditional projection-based techniques. We analyze boundary curvatures and distances in diverse inputs, architectures, and training methods. Boundary distances grow smoothly and slowly with consistent curvature as the size of the subspace increases, suggesting that decision boundaries are close to input samples within large, continuous subspaces. We also quantify how much boundary distances and curvatures reduce near dataset samples after adversarial training. Training methodology has a significantly stronger impact on boundary distance and curvature than architecture or test-set accuracy. These findings are contextualized within prior work, supporting or refuting several previously proposed theories of boundary behavior. Our analytically and empirically supported methodology lays the foundation for future studies to improve network interpretability and understanding.

Explore similar work

CardsList
  1. Understanding the geometry of deep learning with decision boundary volume

    Mar 16, 2026Matthew Burfitt, Jacek Brodzki, Pawel DłotkoDecision Boundary AnalysisNeural Network Generalization

  2. AffineLens: Capturing the Continuous Piecewise Affine Functions of Neural Networks

    May 7, 2026Yi Wei, Xuan Qi, Furao Shen +3Neural Network InterpretabilityNeural Network Approximation Theory

  3. A Geometrical Approach to Constructing Neural Networks for Perfect Training-set Classification

    Oct 12, 2026Akos HajnalNeural Network MemorizationImage Classification