186 citations · 221 across the 6 of their papers we have counts for
3 papers · 1 filter
A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning
Iris A. M. Huijben, Wouter Kool, Max B. Paulus +1
The Gumbel-max trick is a method to draw a sample from a categorical distribution, given by its unnormalized (log-)probabilities. Over the past years, the machine learning communit…
Unbiased Gradient Estimation with Balanced Assignments for Mixtures of Experts
Wouter Kool, Chris J. Maddison, Andriy Mnih
Training large-scale mixture of experts models efficiently on modern hardware requires assigning datapoints in a batch to different experts, each with a limited capacity. Recently…
Deep Policy Dynamic Programming for Vehicle Routing Problems
Wouter Kool, Herke van Hoof, Joaquim Gromicho +1
Routing problems are a class of combinatorial problems with many practical applications. Recently, end-to-end deep learning methods have been proposed to learn approximate solution…