演講者：陳瑞彬教授

單　位：國立成功大學統計學系

日　期：2013年2月27日　PM 14:30

地　點：國立高雄大學理學院408室

講　題：Optimizing Latin hypercube designs by particle swarm

摘　要：
Latin hypercube designs (LHDs) are widely used in many applications. As the number of design points or factors becomes large, the total number of LHDs grows exponentially. The large number of feasible designs makes the search for optimal LHDs a difficult discrete optimization problem. To tackle this problem, a new population-based algorithm is proposed. This algorithm is adapted from the standard particle swarm optimization (PSO) and customized for LHD. Thus it is named as LaPSO. Moreover, we accelerate LaPSO via a graphic processing unit (GPU). According to extensive comparisons, the proposed LaPSO is more stable than existing approaches and is capable of improving known results.