Variational Autoencoders with Jointly Optimized Latent Dependency Structure
We propose a method for learning the dependency structure between latent variables in deep latent variable models. Our general modeling and inference framework combines the complementary strengths of deep generative models and probabilistic graphical models. In particular, we express the latent variable space of a variational autoencoder (VAE) in terms of a Bayesian network with a learned, flexible dependency structure. The network parameters, variational parameters as well as the latent topology are optimized simultaneously with a single objective. Inference is formulated via a sampling procedure that produces expectations over latent variable structures and incorporates top-down and bottom-up reasoning over latent variable values. We validate our framework in extensive experiments on MNIST, Omniglot, and CIFAR-10. Comparisons to state-of-the-art structured variational autoencoder baselines show improvements in terms of the expressiveness of the learned model.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Gaussian Copula Variational Autoencoders for Mixed Data
The variational autoencoder (VAE) is a generative model with continuous latent variables where a pair of probabilistic encoder (bottom-up) and decoder (top-down) is jointly learned by stochastic gradient variational Baye…
DecoderAn 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…
DecoderVariational Autoencoders with implicit priors for short-duration text-independent speaker verification
In this work, we exploited different strategies to provide prior knowledge to commonly used generative modeling approaches aiming to obtain speaker-dependent low dimensional representations from short-duration segments o…
Speaker RecognitionSpeaker VerificationText-Independent Speaker VerificationTripletInfoVAE: Information Maximizing Variational Autoencoders
A key advance in learning generative models is the use of amortized inference distributions that are jointly trained with the models. We find that existing training objectives for variational autoencoders can lead to ina…
No Representation without Transformation
We extend the framework of variational autoencoders to represent transformations explicitly in the latent space. In the family of hierarchical graphical models that emerges, the latent space is populated by higher order …