The Information-Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Modeling
نویسندگان
چکیده
A variety of learning objectives have been recently proposed for training generative models. We show that many of them, including InfoGAN, ALI/BiGAN, ALICE, CycleGAN, VAE, β-VAE, adversarial autoencoders, AVB, and InfoVAE, are Lagrangian duals of the same primal optimization problem. This generalization reveals the implicit modeling trade-offs between flexibility and computational requirements being made by these models. Furthermore, we characterize the class of all objectives that can be optimized under certain computational constraints. Finally, we show how this new Lagrangian perspective can explain undesirable behavior of existing methods and provide new principled solutions.
منابع مشابه
Whai: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling
To train an inference network jointly with a deep generative topic model, making it both scalable to big corpus and fast in out-of-sample prediction, we develop Weibull hybrid autoencoding inference (WHAI) for deep latent Dirichlet allocation (DLDA), which infers posterior samples via a hybrid of stochasticgradient MCMC and autoencoding variational Bayes. The generative network of WHAI has a hi...
متن کاملWhai: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling
To train an inference network jointly with a deep generative topic model, making it both scalable to big corpora and fast in out-of-sample prediction, we develop Weibull hybrid autoencoding inference (WHAI) for deep latent Dirichlet allocation, which infers posterior samples via a hybrid of stochastic-gradient MCMC and autoencoding variational Bayes. The generative network of WHAI has a hierarc...
متن کاملWhai: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling
To train an inference network jointly with a deep generative topic model, making it both scalable to big corpora and fast in out-of-sample prediction, we develop Weibull hybrid autoencoding inference (WHAI) for deep latent Dirichlet allocation, which infers posterior samples via a hybrid of stochastic-gradient MCMC and autoencoding variational Bayes. The generative network of WHAI has a hierarc...
متن کاملChannel-Recurrent Autoencoding for Image Modeling
Despite recent successes in synthesizing faces and bedrooms, existing generative models struggle to capture more complex image types (Figure 1), potentially due to the oversimplification of their latent space constructions. To tackle this issue, building on Variational Autoencoders (VAEs), we integrate recurrent connections across channels to both inference and generation steps, allowing the hi...
متن کاملDisentangling Factors of Variation via Generative Entangling
Here we propose a novel model family with the objective of learning to disentangle the factors of variation in data. Our approach is based on the spike-and-slab restricted Boltzmann machine which we generalize to include higher-order interactions among multiple latent variables. Seen from a generative perspective, the multiplicative interactions emulates the entangling of factors of variation. ...
متن کامل