An adaptive dimension reduction algorithm for latent variables of variational autoencoder

11/15/2021
by   Yiran Dong, et al.
9

Constructed by the neural network, variational autoencoder has the overfitting problem caused by setting too many neural units, we develop an adaptive dimension reduction algorithm that can automatically learn the dimension of latent variable vector, moreover, the dimension of every hidden layer. This approach not only apply to the variational autoencoder but also other variants like Conditional VAE(CVAE), and we show the empirical results on six data sets which presents the universality and efficiency of this algorithm. The key advantages of this algorithm is that it can converge the dimension of latent variable vector which approximates the dimension reaches minimum loss of variational autoencoder(VAE), also speeds up the generating and computing speed by reducing the neural units.

READ FULL TEXT

page 1

page 7

page 8

page 9

page 10

page 11

research
09/14/2018

Unsupervised Abstractive Sentence Summarization using Length Controlled Variational Autoencoder

In this work we present a unsupervised approach to summarize sentences i...
research
11/13/2019

A Stable Variational Autoencoder for Text Modelling

Variational Autoencoder (VAE) is a powerful method for learning represen...
research
09/10/2022

Variational Autoencoder Kernel Interpretation and Selection for Classification

This work proposed kernel selection approaches for probabilistic classif...
research
11/29/2018

A Deep Latent-Variable Model Application to Select Treatment Intensity in Survival Analysis

In the following short article we adapt a new and popular machine learni...
research
11/21/2020

Use of Student's t-Distribution for the Latent Layer in a Coupled Variational Autoencoder

A Coupled Variational Autoencoder, which incorporates both a generalized...
research
02/23/2023

Learning Manifold Dimensions with Conditional Variational Autoencoders

Although the variational autoencoder (VAE) and its conditional extension...
research
07/23/2021

Heteroscedastic Temporal Variational Autoencoder For Irregularly Sampled Time Series

Irregularly sampled time series commonly occur in several domains where ...

Please sign up or login with your details

Forgot password? Click here to reset