REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models.
NIPS(2017)
摘要
Learning in models with discrete latent variables is challenging due to high variance gradient estimators. Generally, approaches have relied on control variates to reduce the variance of the REINFORCE estimator. Recent work citep{jang2016categorical, maddison2016concrete} has taken a different approach, introducing a continuous relaxation of discrete variables to produce low-variance, but biased, gradient estimates. In this work, we combine the two approaches through a novel control variate that produces low-variance, emph{unbiased} gradient estimates. Then, we introduce a modification to the continuous relaxation and show that the tightness of the relaxation can be adapted online, removing it as a hyperparameter. We show state-of-the-art variance reduction on several benchmark generative modeling tasks, generally leading to faster convergence to a better final log-likelihood.
更多查看译文
关键词
data augmentation, expectation-maximization algorithm, finite mixture model, hidden Markov model, latent class model, model selection, stochastic block model
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络