Auto-Encoding Variational Bayes

12/20/2013
by   Diederik P. Kingma, et al.
0

How can we perform efficient inference and learning in directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions, and large datasets? We introduce a stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case. Our contributions is two-fold. First, we show that a reparameterization of the variational lower bound yields a lower bound estimator that can be straightforwardly optimized using standard stochastic gradient methods. Second, we show that for i.i.d. datasets with continuous latent variables per datapoint, posterior inference can be made especially efficient by fitting an approximate inference model (also called a recognition model) to the intractable posterior using the proposed lower bound estimator. Theoretical advantages are reflected in experimental results.

READ FULL TEXT
research
06/11/2019

Approximate Variational Inference Based on a Finite Sample of Gaussian Latent Variables

Variational methods are employed in situations where exact Bayesian infe...
research
09/04/2015

Stochastic gradient variational Bayes for gamma approximating distributions

While stochastic variational inference is relatively well known for scal...
research
03/23/2023

Continuous Indeterminate Probability Neural Network

This paper introduces a general model called CIPNN - Continuous Indeterm...
research
01/31/2014

Neural Variational Inference and Learning in Belief Networks

Highly expressive directed latent variable models, such as sigmoid belie...
research
09/12/2018

Discretely Relaxing Continuous Variables for tractable Variational Inference

We explore a new research direction in Bayesian variational inference wi...
research
09/12/2020

Tracking disease outbreaks from sparse data with Bayesian inference

The COVID-19 pandemic provides new motivation for a classic problem in e...
research
09/05/2023

Distributed Variational Inference for Online Supervised Learning

Developing efficient solutions for inference problems in intelligent sen...

Please sign up or login with your details

Forgot password? Click here to reset