Optimal projections for Gaussian discriminants
From MaRDI portal
Publication:6106145
DOI10.1007/S11634-021-00486-ZarXiv2004.03294OpenAlexW4205363756MaRDI QIDQ6106145FDOQ6106145
Francois Kamper, David P. Hofmeyr, Michail C. Melonas
Publication date: 27 June 2023
Published in: Advances in Data Analysis and Classification. ADAC (Search for Journal in Brave)
Abstract: The problem of obtaining optimal projections for performing discriminant analysis with Gaussian class densities is studied. Unlike in most existing approaches to the problem, the focus of the optimisation is on the multinomial likelihood based on posterior probability estimates, which directly captures discriminability of classes. In addition to the more commonly considered problem, in this context, of classification, the unsupervised clustering counterpart is also considered. Finding optimal projections offers utility for dimension reduction and regularisation, as well as instructive visualisation for better model interpretability. Practical applications of the proposed approach show considerable promise for both classification and clustering. Code to implement the proposed method is available in the form of an R package from https://github.com/DavidHofmeyr/OPGD.
Full work available at URL: https://arxiv.org/abs/2004.03294
Cites Work
- Statistical Analysis of Financial Data in S-Plus
- A Limited Memory Algorithm for Bound Constrained Optimization
- Flexible Discriminant Analysis by Optimal Scoring
- Gaussian mixture model classification: a projection pursuit approach
- Title not available (Why is that?)
- Projection pursuit
- Identifying Regression Outliers and Mixtures Graphically
- Discriminant analysis with common principal components
- Title not available (Why is that?)
- Comment
This page was built for publication: Optimal projections for Gaussian discriminants
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6106145)
