Some theory for ordinal embedding

DOI10.3150/15-BEJ792MaRDI QIDQ527459zbMATH OpenFDO

Authors Ery Arias-Castro

Publication date 11 May 2017

Published in Bernoulli (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1501.02861

zbMATH Keywords

dissimilarity comparisonslandmark multidimensional scalingnon-metric multidimensional scaling (MDS)ordinal embedding

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Statistical aspects of big data and data science (62R07) Paired and multiple comparisons; multiple testing (62J15) Functional limit theorems; invariance principles (60F17)

Abstract: Motivated by recent work on ordinal embedding (Kleindessner and von Luxburg, 2014), we derive large sample consistency results and rates of convergence for the problem of embedding points based on triple or quadruple distance comparisons. We also consider a variant of this problem where only local comparisons are provided. Finally, inspired by (Jamieson and Nowak, 2011), we bound the number of such comparisons needed to achieve consistency.

Recommendations

• Ordinal embeddings of minimum relaxation: general properties, trees, and ultrametrics
• Ordinal embeddings of minimum relaxation, general properties, trees, and ultrametrics
• Ordinal Embedding: Approximation Algorithms and Dimensionality Reduction
• Euclidean embedding of co-occurrence data
• Lens depth function and \(k\)-relative neighborhood graph: versatile tools for ordinal data analysis

Cited in

(3)

• The theory of ordinal length
• From Similarity to Distance: Axiom Set, Monotonic Transformations and Metric Determinacy
• Recovering a metric from its full ordinal information

This page was built for publication: Some theory for ordinal embedding

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q527459)