Discrete Variational Autoencoders
Probabilistic models with discrete latent variables naturally capture datasets composed of discrete classes. However, they are difficult to train efficiently, since backpropagation through discrete variables is generally not possible. We present a novel method to train a class of probabilistic models with discrete latent variables using the variational autoencoder framework, including backpropagation through the discrete latent variables. The associated class of probabilistic models comprises an undirected discrete component and a directed hierarchical continuous component. The discrete component captures the distribution over the disconnected smooth manifolds induced by the continuous component. As a result, this class of models efficiently learns both the class of objects in an image, and their specific realization in pixels, from unsupervised data, and outperforms state-of-the-art methods on the permutation-invariant MNIST, Omniglot, and Caltech-101 Silhouettes datasets.
Code (2)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DVAE++: Discrete Variational Autoencoders with Overlapping Transformations
Training of discrete latent variable models remains challenging because passing gradient information through discrete units is difficult. We propose a new class of smoothing transformations based on a mixture of two over…
Image GenerationAn Introduction to Discrete Variational Autoencoders
Variational Autoencoders (VAEs) are well-established as a principled approach to probabilistic unsupervised learning with neural networks. Typically, an encoder network defines the parameters of a Gaussian distributed la…
DecoderCaloDVAE : Discrete Variational Autoencoders for Fast Calorimeter Shower Simulation
Calorimeter simulation is the most computationally expensive part of Monte Carlo generation of samples necessary for analysis of experimental data at the Large Hadron Collider (LHC). The High-Luminosity upgrade of the LH…
EdVAE: Mitigating Codebook Collapse with Evidential Discrete Variational Autoencoders
Codebook collapse is a common problem in training deep generative models with discrete representation spaces like Vector Quantized Variational Autoencoders (VQ-VAEs). We observe that the same problem arises for the alter…
DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors
Boltzmann machines are powerful distributions that have been shown to be an effective prior over binary latent variables in variational autoencoders (VAEs). However, previous methods for training discrete VAEs have used …