{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-general-framework-for-constrained-bayesian","title":"A General Framework for Constrained Bayesian Optimization using Information-based Search","arxiv_id":"1511.09422","date":"2015-11-30","proceeding":null,"authors":["José Miguel Hernández-Lobato","Michael A. Gelbart","Ryan P. Adams","Matthew W. Hoffman","Zoubin Ghahramani"],"abstract":"We present an information-theoretic framework for solving global black-box\noptimization problems that also have black-box constraints. Of particular\ninterest to us is to efficiently solve problems with decoupled constraints, in\nwhich subsets of the objective and constraint functions may be evaluated\nindependently. For example, when the objective is evaluated on a CPU and the\nconstraints are evaluated independently on a GPU. These problems require an\nacquisition function that can be separated into the contributions of the\nindividual function evaluations. We develop one such acquisition function and\ncall it Predictive Entropy Search with Constraints (PESC). PESC is an\napproximation to the expected information gain criterion and it compares\nfavorably to alternative approaches based on improvement in several synthetic\nand real-world problems. In addition to this, we consider problems with a mix\nof functions that are fast and slow to evaluate. These problems require\nbalancing the amount of time spent in the meta-computation of PESC and in the\nactual evaluation of the target objective. We take a bounded rationality\napproach and develop partial update for PESC which trades off accuracy against\nspeed. We then propose a method for adaptively switching between the partial\nand full updates for PESC. This allows us to interpolate between versions of\nPESC that are efficient in terms of function evaluations and those that are\nefficient in terms of wall-clock time. Overall, we demonstrate that PESC is an\neffective algorithm that provides a promising direction towards a unified\nsolution for constrained Bayesian optimization.","url_abs":"http://arxiv.org/abs/1511.09422v2","url_pdf":"http://arxiv.org/pdf/1511.09422v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-general-framework-for-constrained-bayesian","repo_url":"https://github.com/HIPS/Spearmint","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"bayesian-optimization","task_name":"Bayesian Optimization"},{"task_slug":null,"task_name":"CPU"},{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.09422","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}