@inproceedings{discovery10083559,
            note = {This version is the version of record. For information on re-use, please refer to the publisher's terms and conditions.},
         address = {Montreal, QC, Canada},
          volume = {31},
          editor = {S Bengio and H Wallach and H Larochelle and K Grauman and N CesaBianchi and R Garnett},
       booktitle = {Proceedings of the 32nd Conference on Neural Information Processing Systems (NIPS 2018)},
           month = {December},
          series = {Neural Information Processing Systems (NIPS)},
         journal = {Proceedings of the 32nd Conference on Neural Information Processing Systems (NIPS 2018)},
           title = {Maximizing acquisition functions for Bayesian optimization},
            year = {2018},
       publisher = {Neural Information Processing Systems (NIPS)},
            issn = {1049-5258},
          author = {Wilson, JT and Hutter, F and Deisenroth, MP},
        abstract = {Bayesian optimization is a sample-efficient approach to global optimization that
relies on theoretically motivated value heuristics (acquisition functions) to guide
its search process. Fully maximizing acquisition functions produces the Bayes'
decision rule, but this ideal is difficult to achieve since these functions are frequently non-trivial to optimize. This statement is especially true when evaluating
queries in parallel, where acquisition functions are routinely non-convex, highdimensional, and intractable. We first show that acquisition functions estimated
via Monte Carlo integration are consistently amenable to gradient-based optimization. Subsequently, we identify a common family of acquisition functions, including EI and UCB, whose properties not only facilitate but justify use of greedy
approaches for their maximization.},
             url = {https://papers.nips.cc/paper/8194-maximizing-acquisition-functions-for-bayesian-optimization.pdf}
}