MSE Research Project Database

Machine learning and optimization


Project Leader: James Bailey
Staff: James Bailey, Rao Kotagiri, Christopher Leckie
Collaborators: Jeffrey Chan (RMIT University), Ian Davidson (University of California Davis), Tias Guns (Vrijie Universiteit Brussel), Peter Stuckey (Monash University)
Sponsors: Australian Research Council
Primary Contact: James Bailey (baileyj@unimelb.edu.au)
Keywords: machine learning; optimisation
Disciplines: Computing and Information Systems
Domains:

Current decision making approaches often draw on two key technologies:

  • Machine learning
  • Optimization

Machine learning delivers predictive models and forecasts about quantities like demand and yield, given process input. Optimization takes forecasts for demand and yield, as well as other constraints, and delivers optimal policies for action. This project area is exploring how these activities can be more tightly integrated, since they have traditionally been performed independently. The overall aim is to investigate the deep integration of constrained optimization and machine learning, and to provide more effective tools for society to tackle the challenging decision making problems it is facing.