betaFeedback

WorksComputer Science

ββ-number and Its Applications to Data Science

Abstract

In this paper, we introduce a novel metric, ββ-number, designed to measure the "pp-th order dd-dimensional oscillation degree" of a set. For a given set KK in the Euclidean space Rn\mathbb{R}^n, ββ-number is computed by identifying an optimal dd-dimensional plane LL that minimizes the average pp-th order distance of all points in KK to LL. This metric serves as a versatile tool in data science, functioning both as a dimensionality reduction technique to find the optimal pp-th order dd-dimensional subspace and as a measure to characterize data oscillation for classification. We conduct a thorough exploration of ββ-number through theoretical analysis and numerical experiments. Initially, we establish the upper and lower bounds of ββ-number for any set KK, along with its scaling law. We then elucidate the relationships between ββ-number and its related parameters. A key finding of this study is that in discrete settings, when p=2p=2, the dd-dimensional plane determined by ββ-number coincides with that obtained via Principal Component Analysis (PCA), positioning ββ-number as a generalization of PCA. Furthermore, we propose two algorithms for calculating ββ-number in both continuous and discrete settings. We validate our theoretical results through a series of numerical experiments in low-dimensional cases. Finally, we demonstrate the potential of ββ-number in practical data analysis through a dimensionality reduction task and an image classification task.

Paper details

vlnc:W_a499p8n9
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
arXiv nonexclusive license
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Computer Science

Not recorded for this paper

View statement
Looking for related papers…