This is a past event.
Speaker: Professor Xinwei Deng (Virgnia Tech)
We present a new type of experiment involving a sequence of multiple components associated with their quantities. Such experiments and data are emerging in medical study, health care, logistics, and many other disciplines. It often requires simultaneous optimization for both quantities and sequence-orders of several components, which is designed as a new type of factors: Quantitative-Sequence (QS) factors. Due to the large and semi-discrete input spaces for such experiments, it is non-trivial to efficiently identify optimal settings using only a small number of experimental runs. To address these challenges, we propose a novel active learning approach, denote as QS-learning, to enable effective modeling and efficient optimization for experiments with QS factors. The performance of the proposed method is elaborated by a real drug experiment on lymphoma treatment and several simulation studies.
0 people added