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.
GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Generative Adversarial Networks (GAN) have limitations when the goal is to generate sequences of discrete elements. The reason for this is that samples from a distribution on discrete objects such as the multinomial are not differentiable with respect to the distribution parameters. This problem can be avoided by using the Gumbel-softmax distribution, which is a continuous approximation to a multinomial distribution parameterized in terms of the softmax function. In this work, we evaluate the performance of GANs based on recurrent neural networks with Gumbel-softmax output distributions in the task of generating sequences of discrete elements.
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.