Learning to Search in Branch and Bound Algorithms

279 citations recorded by the source corpus.

How researchers see this paper

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

Learning Combinatorial Optimization Algorithms over Graphs (2017, methodology): “[16] He, He, Daume III, Hal, and Eisner, Jason M.”
Exact Combinatorial Optimization with Graph Convolutional Neural Networks (2019, methodology): “mbranchingon the variableat =x4. moreextensivediscussionofB&BbranchingstrategiesinMILP,thereaderisreferredtoAchterberg et al. [3]. 3.3 Markov decision process formulation As remarked by He et al. [24], the sequential decisions made during B&B can be assimilated to a Markovdecisionprocess[25]”
Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon (2018, methodology): “In the simplest case, expert decisions are collected beforehand, but more advanced methods can collect them online to increase stability as previously shown in Marcos Alvarez et al. (2016) and He et al. (2014).”
Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search (2018, background): “[19] learned a node selection policy for branch-and-bound algorithms with imitation learning.”
On learning and branching: a survey (2017, background): “Learn an adaptive and problem-speciﬁc search strategy is the goal of He et al. (2014).”