A stochastic-approximation autoencoder that maximizes the true log-likelihood and uses MCMC-corrected posterior sampling is applied to semi-supervised learning with discrete latent codes, reporting useful but not state-of-the-art MNIST/SVHN accuracy.
Symmetric Variational Autoencoder and Connections to Adversarial Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
A new form of the variational autoencoder (VAE) is proposed, based on the symmetric Kullback-Leibler divergence. It is demonstrated that learning of the resulting symmetric VAE (sVAE) has close connections to previously developed adversarial-learning methods. This relationship helps unify the previously distinct techniques of VAE and adversarially learning, and provides insights that allow us to ameliorate shortcomings with some previously developed adversarial methods. In addition to an analysis that motivates and explains the sVAE, an extensive set of experiments validate the utility of the approach.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Joint-stochastic-approximation Autoencoders with Application to Semi-supervised Learning
A stochastic-approximation autoencoder that maximizes the true log-likelihood and uses MCMC-corrected posterior sampling is applied to semi-supervised learning with discrete latent codes, reporting useful but not state-of-the-art MNIST/SVHN accuracy.