1k citations · 1.9k across the 49 of their papers we have counts for
Showing 2020 · stat.MLShow all
2 papers · 2 filters
stat.ML2020★ 2 cited
Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator
Max B. Paulus, Chris J. Maddison, Andreas Krause
Gradient estimation in models with discrete latent variables is a challenging problem, because the simplest unbiased estimators tend to have high variance. To counteract this, mode…
stat.ML2020★ 23 cited
Gradient Estimation with Stochastic Softmax Tricks
Max B. Paulus, Dami Choi, Daniel Tarlow +2
The Gumbel-Max trick is the basis of many relaxed gradient estimators. These estimators are easy to implement and low variance, but the goal of scaling them comprehensively to larg…