Estimating the Euclidean distortion of an orbit space

2025/06/04 by Blum-Smith, Ben, Derksen, Harm, Mixon, Dustin G. +2 · 2 citations
#FOS: Computer and information sciences #FOS: Mathematics #Functional Analysis (math.FA) #Information Theory (cs.IT) #Metric Geometry (math.MG) #Representation Theory (math.RT)

paper · doi:10.48550/arxiv.2506.04425

Abstract

Given a finite-dimensional inner product space V and a group G of isometries, we consider the problem of embedding the orbit space V/G into a Hilbert space in a way that preserves the quotient metric as well as possible. This inquiry is motivated by applications to invariant machine learning. We introduce several new theoretical tools before using them to tackle various fundamental instances of this problem.

Cited by

• Tropical Invariants for Permutation Group Actions
• Toward bilipshiz geometric models

Related

• Bi-Lipschitz Quotient embedding for Euclidean Group actions on Data
• Max filtering with reflection groups
• Embedding the Heisenberg group into a bounded dimensional Euclidean space with optimal distortion
• Coarse embeddings of quotients by finite group actions
• Determination of the orbit spaces of non-coregular compact linear groups with one relation among the basic polynomial invariants in the P-matrix approach