Variational Composite Autoencoders
نویسندگان
چکیده
Learning in the latent variable model is challenging in the presence of the complex data structure or the intractable latent variable. Previous variational autoencoders can be low effective due to the straightforward encoder-decoder structure. In this paper, we propose a variational composite autoencoder to sidestep this issue by amortizing on top of the hierarchical latent variable model. The experimental results confirm the advantages of the proposed method.
منابع مشابه
Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
Variational Autoencoders (VAEs) are expressive latent variable models that can be used to learn complex probability distributions from training data. However, the quality of the resulting model crucially relies on the expressiveness of the inference model. We introduce Adversarial Variational Bayes (AVB), a technique for training Variational Autoencoders with arbitrarily expressive inference mo...
متن کاملHow to Train Deep Variational Autoencoders and Probabilistic Ladder Networks
Variational autoencoders are a powerful framework for unsupervised learning. However, previous work has been restricted to shallow models with one or two layers of fully factorized stochastic latent variables, limiting the flexibility of the latent representation. We propose three advances in training algorithms of variational autoencoders, for the first time allowing to train deep models of up...
متن کاملVariational autoencoders for tissue heterogeneity exploration from (almost) no preprocessed mass spectrometry imaging data
The paper presents the application of Variational Autoencoders (VAE) for data dimensionality reduction and explorative analysis of mass spectrometry imaging data (MSI). The results confirm that VAEs are capable of detecting the patterns associated with the different tissue sub-types with better performance than standard approaches.
متن کاملChallenges with Variational Autoencoders for Text
We study variational autoencoders for text data to build a generative model that can be used to conditionally generate text. We introduce a mutual information criterion to encourage the model to put semantic information into the latent representation, and compare its efficacy with other tricks explored in literature such as KL divergence cost annealing and word dropout. We compare the log-likel...
متن کاملDebiasing Evidence Approximations: on Importance-weighted Autoencoders and Jackknife Variational Inference
The importance-weighted autoencoder (IWAE) approach of Burda et al. (2015) defines a sequence of increasingly tighter bounds on the marginal likelihood of latent variable models. Recently, Cremer et al. (2017) reinterpreted the IWAE bounds as ordinary variational evidence lower bounds (ELBO) applied to increasingly accurate variational distributions. In this work, we provide yet another perspec...
متن کامل