Activity Number:
|
440
- Contributed Poster Presentations: Section on Statistics in Defense and National Security
|
Type:
|
Contributed
|
Date/Time:
|
Wednesday, August 10, 2022 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Statistics in Defense and National Security
|
Abstract #322439
|
|
Title:
|
A Flexible Bayesian Multiclass Classification Model
|
Author(s):
|
Frank W Marrs* and Devin Francom
|
Companies:
|
Los Alamos National Lab and Los Alamos National Lab
|
Keywords:
|
splines;
nonparameteric;
RJMCMC;
MARS
|
Abstract:
|
We present a novel Bayesian model for the problem of multiclass classification. In this model, class membership (the response) is determined by the maxima of a latent multivariate normal distribution. The mean functions of this latent normal distribution are combinations of highly flexible basis functions: multivariate adaptive regression splines (MARS), first developed for multiple regression by Friedman. We use reversible jump Markov chain Monte Carlo to make inference on the classification model, including the number of basis functions. We compare the performance of our proposed approach to existing methods on simulated data and a data set of high fidelity storm surge model runs.
|
Authors who are presenting talks have a * after their name.