2015/11/17 by Doniyor Ulmasov, Ulmasov, Doniyor, Caroline Baroukh +7
Computer Science · #Advanced Multi-Objective Optimization Algorithms #Artificial Intelligence (cs.AI) #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Metaheuristic Optimization Algorithms Research #Optimization and Control (math.OC)
paper · pdf · doi:10.48550/arxiv.1511.05385
openalex publication_date 2015/11/17 · openalex created_date 2022/10/04 · openalex updated_date 2026/07/28
Bayesian Optimization (BO) is a data-efficient method for global black-box\noptimization of an expensive-to-evaluate fitness function. BO typically assumes\nthat computation cost of BO is cheap, but experiments are time consuming or\ncostly. In practice, this allows us to optimize ten or fewer critical\nparameters in up to 1,000 experiments. But experiments may be less expensive\nthan BO methods assume: In some simulation models, we may be able to conduct\nmultiple thousands of experiments in a few hours, and the computational burden\nof BO is no longer negligible compared to experimentation time. To address this\nchallenge we introduce a new Dimension Scheduling Algorithm (DSA), which\nreduces the computational burden of BO for many experiments. The key idea is\nthat DSA optimizes the fitness function only along a small set of dimensions at\neach iteration. This DSA strategy (1) reduces the necessary computation time,\n(2) finds good solutions faster than the traditional BO method, and (3) can be\nparallelized straightforwardly. We evaluate the DSA in the context of\noptimizing parameters of dynamic models of microalgae metabolism and show\nfaster convergence than traditional BO.\n