DELBO: Efficient Score Algorithm for Feature Selection on Latent Variables of VAE

In this paper, we develop the notion of the difference of evidence lower bounds (DELBO), based on which an efficient score algorithm is presented to implement feature selection on latent variables of VAE and its variants. Furthermore, we propose marginalization approximation algorithms to optimize V...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2025-09, Vol.47 (9), p.7626-7642
Main Authors: Dong, Yiran, Gao, Chuanhou
Format: Article
Language:English
Subjects:
Approximation algorithms
Classification algorithms
Covariance matrices
Decoding
DELBO feature selection
Feature extraction
Laplace equations
Lower bound
marginalization approximation algorithm
Neural networks
the difference of evidence lower bounds
Training
variational autoencoder
Vectors
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!