14 code implementations • ICLR 2019 • 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.
4 code implementations • 14 Mar 2019 • Wouter Kool, Herke van Hoof, Max Welling
We show how to implicitly apply this 'Gumbel-Top-$k$' trick on a factorized distribution over sequences, allowing to draw exact samples without replacement using a Stochastic Beam Search.
no code implementations • ICLR Workshop drlStructPred 2019 • Wouter Kool, Herke van Hoof, Max Welling
REINFORCE can be used to train models in structured prediction settings to directly optimize the test-time objective.
1 code implementation • ICLR 2020 • 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.
2 code implementations • NeurIPS 2021 • Wouter Kool, Herke van Hoof, Joaquim Gromicho, Max Welling
Routing problems are a class of combinatorial problems with many practical applications.
no code implementations • NeurIPS Workshop ICBINB 2021 • 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.
1 code implementation • 4 Oct 2021 • Iris A. M. Huijben, Wouter Kool, Max B. Paulus, Ruud J. G. van Sloun
The Gumbel-max trick is a method to draw a sample from a categorical distribution, given by its unnormalized (log-)probabilities.
2 code implementations • 22 Nov 2023 • Niels A. Wouda, Leon Lan, Wouter Kool
We hope that PyVRP enables researchers and practitioners to easily and quickly build on a state-of-the-art VRP solver.