paper-with-me

Papers

Quantitative Bounds for Sorting-Based Permutation-Invariant Embeddings

2025-10-25 · Nadav Dym, Matthias Wellershoff, Efstratios Tsoukanis, Daniel Levy, Radu Balan arxiv

We study permutation-invariant embeddings of $d$-dimensional point sets, which are defined by sorting $D$ independent one-dimensional projections of the input. Such embeddings arise in graph deep learning where outputs should be invariant to permutations of graph nodes. Previous work showed that for large enough $D$ and projections in general position, this mapping is injective, and moreover satisfies a bi-Lipschitz condition. However, two gaps remain: firstly, the optimal size $D$ required for injectivity is not yet known, and secondly, no estimates of the bi-Lipschitz constants of the mapping are known. In this paper, we make substantial progress in addressing both of these gaps. Regarding the first gap, we improve upon the best known upper bounds for the embedding dimension $D$ necessary for injectivity, and also provide a lower bound on the minimal injectivity dimension. Regarding the second gap, we construct matrices of projection vectors, so that the bi-Lipschitz distortion of the mapping depends quadratically on the number of points $n$, and is completely independent of the dimension $d$. We also show that for any choice of projection vectors, the distortion of the mapping will never be better than a bound proportional to the square root of $n$. Finally, we show that similar guarantees can be provided even when linear projections are applied to the mapping to reduce its dimension.

📄 PDF Abstract BibTeX arXiv:2510.22186

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Permutation Invariant Representations with Applications to Graph Deep Learning

2022-03-14 · Radu Balan, Naveed Haghani, Maneesh Singh

This paper presents primarily two Euclidean embeddings of the quotient space generated by matrices that are identified modulo arbitrary row permutations. The original application is in deep learning on graphs where the l…

Deep Learning

When and How to Canonize: A Generalization Perspective

2026-05-10 · Yonatan Sverdlov, Benjamin Friedman, Snir Hordan, Nadav Dym arxiv

While invariant architectures are standard for processing symmetric data, there is growing interest in achieving invariance by applying group averaging or canonization to non-invariant backbones. However, the theoretical…

Learning Representations of Sets through Optimized Permutations

2018-12-10 · ICLR 2019 5 · Yan Zhang, Jonathon Hare, Adam Prügel-Bennett

Representations of sets are challenging to learn because operations on sets should be permutation-invariant. To this end, we propose a Permutation-Optimisation module that learns how to permute a set end-to-end. The perm…

General ClassificationQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Permutation invariant functions: statistical tests, density estimation, and computationally efficient embedding

2024-03-04 · Wee Chaimanowong, Ying Zhu

Permutation invariance is among the most common symmetry that can be exploited to simplify complex problems in machine learning (ML). There has been a tremendous surge of research activities in building permutation invar…

Density EstimationDimensionality Reduction

Stability of sorting based embeddings

2024-10-07 · Radu Balan, Efstratios Tsoukanis, Matthias Wellershoff

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 $\alpha : \mathbb{R}^{M \times N} \to \mathbb{R}^D$…