For best experience please turn on javascript and use a modern browser!
You are using a browser that is no longer supported by Microsoft. Please upgrade your browser. The site may not present itself correctly if you continue browsing.
On the interplay between learning and optimization and its effect on MIP solving
Abstract at the OPTIMAL Conference, December 19, 2023
Speaker: Andrea Lodi (Cornell)
Title: On the interplay between learning and optimization and its effect on MIP solving
The last decade has witnessed the impressive development of machine learning (ML) techniques - successfully applied to traditional statistical learning tasks as image recognition and leading to breakthroughs like the famous AlphaGo system. Motivated by those successes, many scientific disciplines have started to investigate the potential for the use of a large amount of data crunched by ML techniques in their context. Combinatorial optimization (CO) has been no exception to this trend, and the ML use in CO has been analyzed from many different angles with various levels of success. In the first part of the talk, we will review the state of the art of this scientific path, interpreting the level of maturity reached by the integration of ML techniques in CO and discussing the challenges. In the second part, we will discuss a tight integration between learning and optimization that is developed in three steps. First, Neural Networks (NNs) are used to learn the representation of some constraints of a CO problem. Second, mathematical programming techniques are used to prune the NNs to obtain a more manageable constraint representation. Third, the resulting CO problem with learned constraints is solved by a solver, in the specific case Gurobi.
Cookie Consent
The UvA uses cookies to ensure the basic functionality of the site and for statistical and optimisation purposes. Cookies are also placed to display third-party content and for marketing purposes. Click 'Accept all cookies' to consent to the placement of all cookies, or choose 'Decline' to only accept functional and analytical cookies. Also read the UvA Privacy statement.