Published in preprint, 2022
This paper introduces a Julia library of Machine Learning for Operations Research, as well as a new probabilistic approach.
Recommended citation: Guillaume Dalle, Léo Baty, Louis Bouvier, Axel Parmentier, "Learning with Combinatorial Optimization Layers: a Probabilistic Approach" https://arxiv.org/pdf/2207.13513.pdf
Published in preprint, 2022
This paper is the fruit of a partnership with Renault.
Recommended citation: Louis Bouvier, Guillaume Dalle, Axel Parmentier, Thibaut Vidal, "Solving a Continent-Scale Inventory Routing Problem at Renault" https://arxiv.org/pdf/2209.00412.pdf
Published:
We consider a large-scale multi-depot multi-commodity Inventory Routing Problem (IRP) to model the packaging return logistics of a major European car manufacturer. No algorithm is known to properly scale to our context. We propose a Large Neighborhood Search (LNS) based on common routing neighborhoods and two new ones: the reinsertion of a customer and a commodity in the IRP solution. We also try to bypass the heavy computations of the LNS leveraging recent ideas in Machine Learning for Operations Research in structured prediction.
Undergraduate course, Ecole des Ponts ParisTech, 2021
Teaching assistant in optimization for first-year engineering students