Plummer Autoencoders

02/10/2018
by   Emanuele Sansone, et al.
0

Estimating the true density in high-dimensional feature spaces is a well-known problem in machine learning. This work shows that it is possible to formulate the optimization problem as a minimization and use the representational power of neural networks to learn very complex densities. A theoretical bound on the estimation error is given when dealing with finite number of samples. The proposed theory is corroborated by extensive experiments on different datasets and compared against several existing approaches from the families of generative adversarial networks and autoencoder-based models.

READ FULL TEXT

page 7

page 13

research
01/08/2019

Autoencoders and Generative Adversarial Networks for Anomaly Detection for Sequences

We introduce synthetic oversampling in anomaly detection for multi-featu...
research
02/02/2022

Robust Estimation for Nonparametric Families via Generative Adversarial Networks

We provide a general framework for designing Generative Adversarial Netw...
research
07/09/2019

Conditional Independence Testing using Generative Adversarial Networks

We consider the hypothesis testing problem of detecting conditional depe...
research
10/21/2021

On some theoretical limitations of Generative Adversarial Networks

Generative Adversarial Networks have become a core technique in Machine ...
research
06/03/2020

Double Generative Adversarial Networks for Conditional Independence Testing

In this article, we consider the problem of high-dimensional conditional...
research
01/24/2019

Multi-objective training of Generative Adversarial Networks with multiple discriminators

Recent literature has demonstrated promising results for training Genera...

Please sign up or login with your details

Forgot password? Click here to reset