186 citations · 221 across the 6 of their papers we have counts for
6 papers
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…
Estimating Gradients for Discrete Random Variables by Sampling without Replacement
Wouter Kool, Herke van Hoof, Max Welling
We derive an unbiased estimator for expectations over discrete random variables based on sampling without replacement, which reduces variance as it avoids duplicate samples. We sho…
Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement
Wouter Kool, Herke van Hoof, Max Welling
The well-known Gumbel-Max trick for sampling from a categorical distribution can be extended to sample elements without replacement. We show how to implicitly apply this 'Gumbe…
Attention, Learn to Solve Routing Problems!
Wouter Kool, Herke van Hoof, Max Welling
The recently presented idea to learn heuristics for combinatorial optimization problems is promising as it can save costly development. However, to push this idea towards practical…