DGSAN trains an explicit discrete generator by iteratively maximizing an objective that compares the new generator's density to the old one's, avoiding gradient passing through discrete samples.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DGSAN: Discrete Generative Self-Adversarial Network
DGSAN trains an explicit discrete generator by iteratively maximizing an objective that compares the new generator's density to the old one's, avoiding gradient passing through discrete samples.