3 November 2022
Optimisation with constraint learning (OCL) uniquely leverages machine learning (ML) to design optimisation models in which constraints and objectives are directly learned from data, when an explicit expression is unknown. While OCL offers great advantages to design more accurate models, in a faster way, practitioners should also be aware of possible pitfalls and inaccuracies arising from embedding fitted models as optimisation constraints. Divided into 4 parts, the OCL Lab offers theory as well as hands-on tutorials, exemplified on a case study from the World Food Programme. Through the OCL Lab, participants will become familiar with 2 novel Python packages (i) OptiCL to learn and embed constraints and (i) DOFramework to evaluate the optimal solutions generated by an OCL algorithm. The first 2 parts of the lab will provide participants with theoretical and practical knowledge for using ML models to learn constraints and objectives directly from data. The remaining 2 parts will be dedicated to novel quality metrics for OCL and a structured testing framework for OCL algorithms.
In its beginning, the AI field focused on proposing theories of computational intelligence, on designing formal models and algorithms, and on characterizing their behaviour through analysis and experimentation. Today, AI offers a powerful set of modelling tools and decision systems that are having a pervasive impact on a diverse set of real world applications. The purpose of the Lab Forum is to train members of AAAI in using these tools. Often, but not always, tutorials focus on formalisms and algorithms, while labs can focus on teaching methodologies for effectively applying AI tools and modelling frameworks. Labs are often most effectively taught using real world case studies. Also note that tutorials and labs are not exclusive, having tutorials and labs on the same topic can be a powerful combination.
The AAAI Conference on Artificial Intelligence (AAAI) is one of the leading international academic conference in artificial intelligence held annually. Along with ICML, NeurIPS and ICLR, it is one of the primary conferences of high impact in machine learning and artificial intelligence research.
The purpose of the Lab Forum is to train members of AAAI in using artificial intelligence models and algorithms on a diverse set of real world applications. Often, but not always, tutorials focus on formalisms and algorithms, while labs can focus on teaching methodologies for effectively applying AI tools and modelling frameworks. Labs are often most effectively taught using real world case studies. Also note that tutorials and labs are not exclusive, having tutorials and labs on the same topic can be a powerful combination.