# Analysis of Generalizability of Deep Neural Networks Based on the Complexity of Decision Boundary

arXiv: https://arxiv.org/abs/2009.07974 · HTML: https://mlsanity.com/paper/2009.07974/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2020.

## Built on by (most cited first, 13 of 13)

- [Latent Imitator: Generating Natural Individual Discriminatory Instances for Black-Box Fairness Testing](https://mlsanity.com/paper/2305.11602/) (2023)
- [A Novel Intrinsic Measure of Data Separability](https://mlsanity.com/paper/2109.05180/) (2021)
- [Effective Instruction Parsing Plugin for Complex Logical Query Answering on Knowledge Graphs](https://mlsanity.com/paper/2410.20321/) (2024)
- [Understanding Deep Learning via Decision Boundary](https://mlsanity.com/paper/2206.01515/) (2022)
- [Unveiling the Hessian's Connection to the Decision Boundary](https://mlsanity.com/paper/2306.07104/) (2023)
- [The Missing Margin: How Sample Corruption Affects Distance to the Boundary in ANNs](https://mlsanity.com/paper/2302.06925/) (2023)
- [Memory-Optimized Once-For-All Network](https://mlsanity.com/paper/2409.05900/) (2024)
- [Guidelines For The Choice Of The Baseline in XAI Attribution Methods](https://mlsanity.com/paper/2503.19813/) (2025)
- [The Vanishing Decision Boundary Complexity and the Strong First Component](https://mlsanity.com/paper/2211.16209/) (2022)
- [SkelEx and BoundEx: Natural Visualization of ReLU Neural Networks](https://mlsanity.com/paper/2305.05562/) (2023)
- [BFA-YOLO: A balanced multiscale object detection network for building faccade attachments detection](https://mlsanity.com/paper/2409.04025/) (2024)
- [Deep Learning-Based Breast Cancer Detection in Mammography: A Multi-Center Validation Study in Thai Population](https://mlsanity.com/paper/2506.03177/) (2025)
- [Understanding the geometry of deep learning with decision boundary volume](https://mlsanity.com/paper/2603.14768/) (2026)

## Abstract (arXiv)

For supervised learning models, the analysis of generalization ability (generalizability) is vital because the generalizability expresses how well a model will perform on unseen data. Traditional generalization methods, such as the VC dimension, do not apply to deep neural network (DNN) models. Thus, new theories to explain the generalizability of DNNs are required. In this study, we hypothesize that the DNN with a simpler decision boundary has better generalizability by the law of parsimony (Occam's Razor). We create the decision boundary complexity (DBC) score to define and measure the complexity of decision boundary of DNNs. The idea of the DBC score is to generate data points (called adversarial examples) on or near the decision boundary. Our new approach then measures the complexity of the boundary using the entropy of eigenvalues of these data. The method works equally well for high-dimensional data. We use training data and the trained model to compute the DBC score. And, the ground truth for model's generalizability is its test accuracy. Experiments based on the DBC score have verified our hypothesis. The DBC is shown to provide an effective method to measure the complexity of a decision boundary and gives a quantitative measure of the generalizability of DNNs.