Max B. Paulus

Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient\n Estimator

2020 · arXiv (Cornell University)

Gradient estimation in models with discrete latent variables is a challenging\nproblem, because the simplest unbiased estimators tend to have high variance.\nTo counteract this, modern estimators either introduce bias, rely on multiple\nfunction evaluations, or use learned, …