Search Results for author: Wouter Kool

Found 7 papers, 5 papers with code

A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning

1 code implementation4 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.

BIG-bench Machine Learning

Unbiased Gradient Estimation with Balanced Assignments for Mixtures of Experts

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.

Estimating Gradients for Discrete Random Variables by Sampling without Replacement

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.

Structured Prediction

Buy 4 REINFORCE Samples, Get a Baseline for Free!

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.

Structured Prediction

Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement

3 code implementations14 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.

Translation

Attention, Learn to Solve Routing Problems!

12 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.

Combinatorial Optimization

Cannot find the paper you are looking for? You can Submit a new open access paper.