Learning Fast Optimizers for Contextual Stochastic Integer Programs

By Vinod Nair, Dj Dvijotham, Iain Dunning, Oriol Vinyals. 2018

23 citations recorded by the source corpus.

Subfields: Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

1. Simon Lacoste-Julien
2. Andrea Lodi
3. Yoshua Bengio
4. Emma Frejinger
5. Antoine Prouvost
6. François Soumis
7. Dimitris J. Bertsimas
8. Bartolomeo Stellato

Citations in the corpus

• Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information (2018, methodology): “In contrast with the existing alternatives offered by approximate stochastic programming and the recently proposed reinforcement learning approach by Nair et al. (2018), our methodology built on ML anticipates calculations by generating, in advance, a prediction function instead of pointwise solutio”
• A learning-based algorithm to quickly compute good primal solutions for Stochastic Integer Programs (2019, methodology): “Assumption a above is intrinsic to the method in [16], as both the initialization policy and the local move policy of the method involves flipping the bits of the first-stage decision vector.”
• Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon (2018, background): “Nair et al. (2018) take advantage of this repetitive process to learn an end-to-end model to solve the problem.”