Stability of sorting based embeddings
Not on the map. Why?
Abstract (arXiv)
Consider a group G of order M acting unitarily on a real inner product space V. We show that the sorting based embedding obtained by applying a general linear map α : ℝM × N → ℝD to the invariant map β_Phi : V → ℝM × N given by sorting the coorbits (langle v, g φi rangleV)g ∈ G, where (φi)i=1N ∈ V, satisfies a bi-Lipschitz condition if and only if it separates orbits. Additionally, we note that any invariant Lipschitz continuous map (into a Hilbert space) factors through the sorting based embedding, and that any invariant continuous map (into a locally convex space) factors through the sorting based embedding as well.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 10 of its 24 references that are in the map. First posted on arXiv 7 Oct 2024.
Builds on
10 of 24 references.
References · 10
- 2016Group Equivariant Convolutional Networkscited by 1,154
- 2018Why do deep convolutional networks generalize so poorly to small image transformations?cited by 198
- 2018Universal approximations of invariant maps by neural networkscited by 127
- 2021Scalars are universal: Equivariant machine learning, structured like classical physicscited by 127
- 2022Low Dimensional Invariant Embeddings for Universal Geometric Learningcited by 38
- 2022Permutation Invariant Representations with Applications to Graph Deep Learningcited by 20
- 2022Group-invariant max filteringcited by 18
- 2022Machine learning and invariant theorycited by 13
- 2022Group invariant machine learning by fundamental domain projectionscited by 11
- 2013Invertibility and Robustness of Phaseless Reconstructioncited by 3
Built on by
Citing papers per year: 2024: 1; 2025: 2.
3 papers.
- 2024FSW-GNN: A Bi-Lipschitz WL-Equivalent Graph Neural Networkcited by 8
- 2025Quantitative Bounds for Sorting-Based Permutation-Invariant Embeddingscited by 2
- 2025Toward bilipshiz geometric modelscited by 1
- 2025Toward bilipshiz geometric models13 Nov 2025
- 2025Quantitative Bounds for Sorting-Based Permutation-Invariant Embeddings25 Oct 2025
- 2024FSW-GNN: A Bi-Lipschitz WL-Equivalent Graph Neural Network10 Oct 2024