Many real-world problems have complicated objective functions whose optimization requires sophisticated sequential decision-making strategies. Modelling human function learning has been the subject of intense research in cognitive sciences. The topic is relevant in black-box optimization where information about the objective and/or constraints is not available and must be learned through function evaluations. The Gaussian Process based Bayesian learning paradigm is central in the development of active learning approaches balancing exploration/exploitation in uncertain conditions towards effective generalization in large decision spaces. In this paper we focus on Bayesian Optimization and analyse experimentally how it compares to humans while searching for the maximum of an unknown 2D function. A set of controlled experiments with 53 subjects confirm that Gaussian Processes provide a general model to explain different patterns of learning enabled search and optimization in humans.
Candelieri, A., Perego, R., Giordani, I., Archetti, F. (2020). Are Humans Bayesian in the Optimization of Black-Box Functions?. In Numerical Computations: Theory and Algorithms Third International Conference, NUMTA 2019, Crotone, Italy, June 15–21, 2019, Revised Selected Papers, Part II (pp.32-42). Springer [10.1007/978-3-030-40616-5_3].
Are Humans Bayesian in the Optimization of Black-Box Functions?
Candelieri, A
;Perego, R;Giordani, I;Archetti, F
2020
Abstract
Many real-world problems have complicated objective functions whose optimization requires sophisticated sequential decision-making strategies. Modelling human function learning has been the subject of intense research in cognitive sciences. The topic is relevant in black-box optimization where information about the objective and/or constraints is not available and must be learned through function evaluations. The Gaussian Process based Bayesian learning paradigm is central in the development of active learning approaches balancing exploration/exploitation in uncertain conditions towards effective generalization in large decision spaces. In this paper we focus on Bayesian Optimization and analyse experimentally how it compares to humans while searching for the maximum of an unknown 2D function. A set of controlled experiments with 53 subjects confirm that Gaussian Processes provide a general model to explain different patterns of learning enabled search and optimization in humans.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
