Saved in:
Bibliographic Details
Main Authors: Wei, Yi, Qi, Xuan, Shen, Furao, Zhao, Jian, Murino, Vittorio, Beyan, Cigdem
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.06218
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910210791047168
author Wei, Yi
Qi, Xuan
Shen, Furao
Zhao, Jian
Murino, Vittorio
Beyan, Cigdem
author_facet Wei, Yi
Qi, Xuan
Shen, Furao
Zhao, Jian
Murino, Vittorio
Beyan, Cigdem
contents Piecewise affine neural networks (PANNs) provide a principled geometric perspective on neural network expressivity by characterizing the input--output map as a continuous piecewise affine (CPA) function whose complexity is governed by the number, arrangement, and shapes of its affine regions. However, existing interpretability and expressivity analyses often rely on indirect proxies (e.g., activation statistics or theoretical upper bounds) and rarely offer practical, accurate tools for enumerating and visualizing the induced region partition under realistic architectures and bounded input domains. In this work, we present AffineLens, a unified framework for computing the hyperplane arrangements and polyhedral structures underlying PANNs. Given a calibrated (bounded) input polytope, AffineLens identifies the subset of neuron-induced hyperplanes that intersect the domain, enumerates the resulting affine sub-regions in a layer-wise manner, and returns provably non-empty maximal CPA regions together with interior representatives. The framework further provides visualizations of region partitioning and decision boundaries, enabling qualitative inspection alongside quantitative region counts. By exploiting the affine restriction property of CPA networks under fixed activation patterns, AffineLens supports a broad class of modern components, including batch normalization, pooling, residual connections, multilayer perceptrons, and convolutional layers. Finally, we use AffineLens to perform a systematic empirical study of architectural expressivity, comparing networks through region complexity metrics and revealing how design choices influence the geometry of learned functions.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06218
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AffineLens: Capturing the Continuous Piecewise Affine Functions of Neural Networks
Wei, Yi
Qi, Xuan
Shen, Furao
Zhao, Jian
Murino, Vittorio
Beyan, Cigdem
Machine Learning
Piecewise affine neural networks (PANNs) provide a principled geometric perspective on neural network expressivity by characterizing the input--output map as a continuous piecewise affine (CPA) function whose complexity is governed by the number, arrangement, and shapes of its affine regions. However, existing interpretability and expressivity analyses often rely on indirect proxies (e.g., activation statistics or theoretical upper bounds) and rarely offer practical, accurate tools for enumerating and visualizing the induced region partition under realistic architectures and bounded input domains. In this work, we present AffineLens, a unified framework for computing the hyperplane arrangements and polyhedral structures underlying PANNs. Given a calibrated (bounded) input polytope, AffineLens identifies the subset of neuron-induced hyperplanes that intersect the domain, enumerates the resulting affine sub-regions in a layer-wise manner, and returns provably non-empty maximal CPA regions together with interior representatives. The framework further provides visualizations of region partitioning and decision boundaries, enabling qualitative inspection alongside quantitative region counts. By exploiting the affine restriction property of CPA networks under fixed activation patterns, AffineLens supports a broad class of modern components, including batch normalization, pooling, residual connections, multilayer perceptrons, and convolutional layers. Finally, we use AffineLens to perform a systematic empirical study of architectural expressivity, comparing networks through region complexity metrics and revealing how design choices influence the geometry of learned functions.
title AffineLens: Capturing the Continuous Piecewise Affine Functions of Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2605.06218