☆ 4.5 Article

A closed-form solution for conditional multidimensional scaling

PATTERN RECOGNITION LETTERS (2022)

Distance-Based Statistical Inference

Marianthi Markatou et al.

Summary: Statistical distances have a long history and are crucial in estimation, hypothesis testing, and model selection. This review discusses the properties of commonly used statistical distances and their application in model-based inference. Special emphasis is placed on identifying statistical distances that can be interpreted as loss functions for model assessment.

ANNUAL REVIEW OF STATISTICS AND ITS APPLICATION, VOL 8, 2021 (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Geometry and statistics-preserving manifold emb e dding for nonlinear dimensionality reduction

Md Tauhidul Islam et al.

Summary: This paper introduces a novel nonlinear dimensionality reduction method, GSE, which aims to preserve both geometry and statistics of the data while overcoming some critical limitations of traditional methods. Experimental results show that GSE provides significantly better manifold embedding results than traditional methods on several datasets.

PATTERN RECOGNITION LETTERS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence