Variational Composite Autoencoders

04/12/2018
by   Jiangchao Yao, et al.
0

Learning in the latent variable model is challenging in the presence of the complex data structure or the intractable latent variable. Previous variational autoencoders can be low effective due to the straightforward encoder-decoder structure. In this paper, we propose a variational composite autoencoder to sidestep this issue by amortizing on top of the hierarchical latent variable model. The experimental results confirm the advantages of our model.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/06/2019

An Introduction to Variational Autoencoders

Variational autoencoders provide a principled framework for learning dee...
research
10/23/2020

Generating Long Financial Report using Conditional Variational Autoencoders with Knowledge Distillation

Automatically generating financial report from a piece of news is quite ...
research
03/06/2023

Guiding Energy-based Models via Contrastive Latent Variables

An energy-based model (EBM) is a popular generative framework that offer...
research
12/06/2022

Three Variations on Variational Autoencoders

Variational autoencoders (VAEs) are one class of generative probabilisti...
research
05/17/2017

Learning a Hierarchical Latent-Variable Model of 3D Shapes

We propose the Variational Shape Learner (VSL), a hierarchical latent-va...
research
08/23/2019

Increasing the Generalisaton Capacity of Conditional VAEs

We address the problem of one-to-many mappings in supervised learning, w...
research
05/09/2022

Posterior Collapse of a Linear Latent Variable Model

This work identifies the existence and cause of a type of posterior coll...

Please sign up or login with your details

Forgot password? Click here to reset