Persistent Homology and the Upper Box Dimension
Not on the map. Why?
Abstract (arXiv)
We introduce a fractal dimension for a metric space defined in terms of the persistent homology of extremal subsets of that space. We exhibit hypotheses under which this dimension is comparable to the upper box dimension; in particular, the dimensions coincide for subsets of ℝ2 whose upper box dimension exceeds 1.5. These results are related to extremal questions about the number of persistent homology intervals of a set of n points in a metric space.
Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Feb 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 2; 2023: 4; 2024: 1; 2025: 4; 2026: 2.
15 papers.
Sort:
- 2023Intrinsic Dimension Estimation for Robust Detection of AI-Generated Textscited by 111
- 2021Intrinsic Dimension, Persistent Homology and Generalization in Neural Networkscited by 70
- 2023The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Modelscited by 37
- 2023Generalization Bounds with Data-dependent Fractal Dimensionscited by 15
- 2023Metric Space Magnitude and Generalisation in Neural Networkscited by 15
- 2022Predicting the generalization gap in neural networks using topological data analysiscited by 9
- 2024On the Limitations of Fractal Dimension as a Measure of Generalizationcited by 5
- 2021Topology Applied to Machine Learning: From Global to Localcited by 4
- 2025Memorization in Language Models through the Lens of Intrinsic Dimensioncited by 3
- 2025T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learningcited by 2
- 2025When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detectioncited by 1
- 2025Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Storycited by 1
3 more
- 2022On topological data analysis for structural dynamics: an introduction to persistent homologycited by 0
- 2026What Makes a Good Layer? Assessing the Layer-Wise Intrinsic Properties of Music Foundation Modelscited by 0
- 2026Linear Probing Provides Robust and Efficient Detection of Machine-Generated Textcited by 0
- 2026Linear Probing Provides Robust and Efficient Detection of Machine-Generated Text25 Aug 2026
- 2026What Makes a Good Layer? Assessing the Layer-Wise Intrinsic Properties of Music Foundation Models14 Aug 2026
- 2025Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story19 Nov 2025
- 2025T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learning27 Oct 2025
- 2025When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection14 Oct 2025
- 2025Memorization in Language Models through the Lens of Intrinsic Dimension11 Jun 2025
- 2024On the Limitations of Fractal Dimension as a Measure of Generalization4 Jun 2024
- 2023The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models10 Nov 2023
- 2023Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts7 Jun 2023
- 2023Metric Space Magnitude and Generalisation in Neural Networks9 May 2023
- 2023Generalization Bounds with Data-dependent Fractal Dimensions6 Feb 2023
- 2022On topological data analysis for structural dynamics: an introduction to persistent homology12 Sep 2022
- 2023Intrinsic Dimension Estimation for Robust Detection of AI-Generated Textscited by 111
- 2021Intrinsic Dimension, Persistent Homology and Generalization in Neural Networkscited by 70
- 2023The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Modelscited by 37
- 2023Generalization Bounds with Data-dependent Fractal Dimensionscited by 15
- 2023Metric Space Magnitude and Generalisation in Neural Networkscited by 15
- 2022Predicting the generalization gap in neural networks using topological data analysiscited by 9
- 2024On the Limitations of Fractal Dimension as a Measure of Generalizationcited by 5
- 2021Topology Applied to Machine Learning: From Global to Localcited by 4
- 2025Memorization in Language Models through the Lens of Intrinsic Dimensioncited by 3
- 2025T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learningcited by 2
- 2025When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detectioncited by 1
- 2025Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Storycited by 1
12 most cited of 15 All 15 (JSON)
- 2026Linear Probing Provides Robust and Efficient Detection of Machine-Generated Text25 Aug 2026
- 2026What Makes a Good Layer? Assessing the Layer-Wise Intrinsic Properties of Music Foundation Models14 Aug 2026
- 2025Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story19 Nov 2025
- 2025T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learning27 Oct 2025
- 2025When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection14 Oct 2025
- 2025Memorization in Language Models through the Lens of Intrinsic Dimension11 Jun 2025
- 2024On the Limitations of Fractal Dimension as a Measure of Generalization4 Jun 2024
- 2023The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models10 Nov 2023
- 2023Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts7 Jun 2023
- 2023Metric Space Magnitude and Generalisation in Neural Networks9 May 2023
- 2023Generalization Bounds with Data-dependent Fractal Dimensions6 Feb 2023
- 2022On topological data analysis for structural dynamics: an introduction to persistent homology12 Sep 2022
12 newest of 15 All 15 (JSON)