Learning Latent Space Energy-Based Prior Model

by   Bo Pang, et al.

The generator model assumes that the observed example is generated by a low-dimensional latent vector via a top-down network, and the latent vector follows a simple and known prior distribution, such as uniform or Gaussian white noise distribution. While we can learn an expressive top-down network to map the prior distribution to the data distribution, we can also learn an expressive prior model instead of assuming a given prior distribution. This follows the philosophy of empirical Bayes where the prior model is learned from the observed data. We propose to learn an energy-based prior model for the latent vector, where the energy function is parametrized by a very simple multi-layer perceptron. Due to the low-dimensionality of the latent space, learning a latent space energy-based prior model proves to be both feasible and desirable. In this paper, we develop the maximum likelihood learning algorithm and its variation based on short-run Markov chain Monte Carlo sampling from the prior and the posterior distributions of the latent vector, and we show that the learned model exhibits strong performance in terms of image and text generation and anomaly detection.


page 2

page 7

page 9

page 10


A Tale of Two Latent Flows: Learning Latent Space Normalizing Flow with Short-run Langevin Flow for Approximate Inference

We study a normalizing flow in the latent space of a top-down generator ...

Adaptive Multi-stage Density Ratio Estimation for Learning Latent Space Energy-based Model

This paper studies the fundamental problem of learning energy-based mode...

Inferring Multi-Dimensional Rates of Aging from Cross-Sectional Data

Modeling how individuals evolve over time is a fundamental problem in th...

Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space

Modern Generative Adversarial Networks are capable of creating artificia...

Likelihood-Based Generative Radiance Field with Latent Space Energy-Based Model for 3D-Aware Disentangled Image Representation

We propose the NeRF-LEBM, a likelihood-based top-down 3D-aware 2D image ...

Normalizing flow sampling with Langevin dynamics in the latent space

Normalizing flows (NF) use a continuous generator to map a simple latent...

Consistency of Maximum Likelihood for Continuous-Space Network Models

Network analysis needs tools to infer distributions over graphs of arbit...

Please sign up or login with your details

Forgot password? Click here to reset