Presenting new optimization approaches for tree ensembles

PhD Candidate Matt Raymond presented his research poster at the 2024 MSSISS Symposium. His work, “Joint Optimization of Piecewise Linear Ensembles”, proposes a new optimization approach to improve the performance of gradient boosted ensembles. These machine learning models are state-of-the-art in many settings, so any performance gains will provide direct improvements in many fields. This work was performed with the help of Matt’s co-advisors, Prof. Clayton Scott and Prof. Angela Violi.