stats:gumbel-max_trick
This is an old revision of the document!
Gumbel-max Trick
See Gumbel-max trick at Tim Vieira's blog, and this follow-up post on Weighted reservoir sampling.
The Gumbel-max trick is widely used in deep learning from this paper: Categorical Reparameterization with Gumbel-Softmax. See also the Reparameterization Trick section 6.4 in Kim et al 2018 - A Tutorial on Deep Latent Variable Models of Natural Language
stats/gumbel-max_trick.1610035914.txt.gz · Last modified: 2023/06/15 07:36 (external edit)