This is a talk given by Prof Emma Frejinger as part of the Online Seminar Series Machine Learning NeEDS Mathematical Optimization, https://congreso.us.es/mlneedsmo/
In practice, it is often essential to take operational decisions and constraints into account when solving tactical decision-making problems. However, at the tactical level, there is imperfect information about the operational decision-making problems. Transport applications are a rich source of such tactical problems, and they are typically of large scale with difficult operational decision-making problems. In this talk we will use railway transport planning as an illustration.
We propose a methodology at the nexus of operations research and machine learning (ML) leveraging generic approximators available from ML to accelerate the solution of mixed-integer linear two-stage stochastic programs. We aim at solving problems where the second stage is highly demanding. Our core idea is to gain large reductions in online solution time while incurring small reductions in first-stage solution accuracy by substituting the exact second-stage solutions with fast, yet accurate supervised ML predictions. This upfront investment in ML would be justified when similar problems are solved repeatedly over time, for example, in transport planning related to fleet management, routing and container yard management. The proposed method can solve the hardest benchmark instances, on average, in 9-20% of the time it takes the state-of-the-art exact method. Average optimality gaps are in most cases less than 0.1%.
Link to the talk: https://eu.bbcollab.com/guest/0ea23ac069c1444b95d7e0b1f4dd06a7
The organizers of the Online Seminar Series Machine Learning NeEDS Mathematical Optimization
Emilio Carrizosa, IMUS-Instituto de Matemáticas de la Universidad de Sevilla
Thomas Halskov, Copenhagen Business School
Kseniia Kurishchenko, Copenhagen Business School
Cristina Molero-Río, IMUS-Instituto de Matemáticas de la Universidad de Sevilla
Jasone Ramírez-Ayerbe, IMUS-Instituto de Matemáticas de la Universidad de Sevilla
Dolores Romero Morales, Copenhagen Business School