ML4CO submission EFPP

Research output: Chapter in Book/Report/Conference proceedingConference PaperOther

Abstract

This paper presents our submission to ML4CO, a branching rule that exploits the structure within a problem class via a graph neural network that is trained using a distributional reinforcement learning algorithm. The learned branching rule participated in the dual bound challenge, ranking third among 23 entries. Experiments on the ML4CO instances show that it performs between 16% and 34% better on average than the default reliability pseudocost branching in the state-of-the-art academic solver SCIP.
Original languageEnglish
Title of host publicationMachine Learning for Combinatorial Optimization
Subtitle of host publicationNeurIPS 2021 Competition Workshop
Place of PublicationSan Diego CA USA
PublisherNeural Information Processing Systems (NIPS)
Number of pages4
Publication statusPublished - 2021
EventAdvances in Neural Information Processing Systems 2021 - Online, United States of America
Duration: 7 Dec 202110 Dec 2021
Conference number: 35th
https://papers.nips.cc/paper/2021 (Proceedings)
https://nips.cc/Conferences/2021 (Website)

Conference

ConferenceAdvances in Neural Information Processing Systems 2021
Abbreviated titleNeurIPS 2021
Country/TerritoryUnited States of America
CityOnline
Period7/12/2110/12/21
Internet address

Cite this