Top-k Ranking Bayesian Optimization
Keywords:Active Learning, Learning Preferences or Rankings, Bayesian Learning, Human-in-the-loop Machine Learning
AbstractThis paper presents a novel approach to top-k ranking Bayesian optimization (top-k ranking BO) which is a practical and significant generalization of preferential BO to handle top-k ranking and tie/indifference observations. We first design a surrogate model that is not only capable of catering to the above observations, but is also supported by a classic random utility model. Another equally important contribution is the introduction of the first information-theoretic acquisition function in BO with preferential observation called multinomial predictive entropy search (MPES) which is flexible in handling these observations and optimized for all inputs of a query jointly. MPES possesses superior performance compared with existing acquisition functions that select the inputs of a query one at a time greedily. We empirically evaluate the performance of MPES using several synthetic benchmark functions, CIFAR-10 dataset, and SUSHI preference dataset.
How to Cite
Nguyen, Q. P., Tay, S., Low, B. K. H., & Jaillet, P. (2021). Top-k Ranking Bayesian Optimization. Proceedings of the AAAI Conference on Artificial Intelligence, 35(10), 9135-9143. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17103
AAAI Technical Track on Machine Learning III