On learning and branching: a survey

By Andrea Lodi, Giulia Zarpellon. 2017

212 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Science and Operations Research, Numerical Analysis, 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 Artificial Intelligence

In Management Science and Operations Research

In Numerical Analysis

In Reinforcement Learning

Citations in the corpus

Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information (2018, methodology): “On the one hand, ML is used as a tool for approximating complex and time-consuming tasks in OR algorithms, arguably the most important one being branching for enumerative approaches to NP-hard problems (see, e.g., Lodi and Zarpellon, 2017, for a survey).”
Optimization Models for Machine Learning: A Survey (2019, background): “This paper also complements the recent surveys of [42, 76, 215] which described methodological developments for solving machine learning optimization problems; [20, 154] which discussed how machine learning advanced the solution approaches of mathematical programming; [70] which described the intera”
Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon (2018, background): “This is clearly the context of the branch-and-bound tree for MILP, where we already mentioned how the task of selecting the branching variable is either too heuristic or too slow, and is therefore a good candidate for learning (Lodi and Zarpellon, 2017).”
Exact Combinatorial Optimization with Graph Convolutional Neural Networks (2019, methodology): “…on variable selection, also known as the branching problem , which lies at the core of the B&B paradigm yet is still not well theoretically understood [41], and adopt an imitation learning strategy to learn a fast approximation of strong branching , a high-quality but expensive branching rule.”
Combinatorial optimization and reasoning with graph neural networks (2021, background): “[9] give a high-level overview of machine learning methods for CO, without signi cantly concentrating on graph-structured input, while [80] focuses on machine learning for branching in the context of mixed integer programming.”