{"id":{"repo_id":"penn","oai_identifier":"oai:repository.upenn.edu:20.500.14332/62344"},"canonical_url":"https://search.dev.ndltd.org/etd/penn/oai:repository.upenn.edu:20.500.14332/62344","repository":{"repo_id":"penn","name":"University of Pennsylvania","base_url":"https://repository.upenn.edu/server/oai/request"},"display":{"title":"Generative Bayesian Optimization for Structured Design","abstract":"Black-box optimization is a general framework for problems where our goal is to find an input that maximizes some real-valued objective function. Typically, no mathematical form is available for this objective function, and it may be expensive to evaluate, making it a black-box. Many practical scientific discovery problems can be framed as black-box optimization. For example, in drug discovery one might seek to design a small molecule that maximizes a real-valued objective function, such as predicted therapeutic activity against a target pathogen. Such objectives lack closed-form expressions and may require costly physics-based simulations or laboratory experiments to evaluate, motivating sample-efficient optimization methods. Bayesian optimization (BO) is a widely used machine learning method for sample-efficient black-box optimization. However, standard BO methods assume a continuous, numerical input space and are not directly applicable to structured, discrete domains such as molecules or proteins. Latent space Bayesian optimization (LS-BO) is a newly emerging approach for this setting. LS-BO employs generative models to embed discrete, structured inputs into continuous latent spaces where BO techniques can be applied. This dissertation presents recent work that advances LS-BO, enabling more effective optimization of challenging real-world objectives in scientific discovery. In addition, it extends the LS-BO framework to new problem settings that broaden its applicability and better align with the practical needs of scientific practitioners.","abstract_html":"Black-box optimization is a general framework for problems where our goal is to find an input that maximizes some real-valued objective function. Typically, no mathematical form is available for this objective function, and it may be expensive to evaluate, making it a black-box. Many practical scientific discovery problems can be framed as black-box optimization. For example, in drug discovery one might seek to design a small molecule that maximizes a real-valued objective function, such as predicted therapeutic activity against a target pathogen. Such objectives lack closed-form expressions and may require costly physics-based simulations or laboratory experiments to evaluate, motivating sample-efficient optimization methods. Bayesian optimization (BO) is a widely used machine learning method for sample-efficient black-box optimization. However, standard BO methods assume a continuous, numerical input space and are not directly applicable to structured, discrete domains such as molecules or proteins. Latent space Bayesian optimization (LS-BO) is a newly emerging approach for this setting. LS-BO employs generative models to embed discrete, structured inputs into continuous latent spaces where BO techniques can be applied. This dissertation presents recent work that advances LS-BO, enabling more effective optimization of challenging real-world objectives in scientific discovery. In addition, it extends the LS-BO framework to new problem settings that broaden its applicability and better align with the practical needs of scientific practitioners.","abstract_has_math":false,"creators":["Maus, Natalie"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Gardner, Jacob, R"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025","date_published":"2025","updated_at":"2026-07-24T03:47:51Z","subjects":["Computer Sciences"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://repository.upenn.edu/handle/20.500.14332/62344","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Gardner, Jacob, R"]},{"key":"dc:creator","label":"Author","values":["Maus, Natalie"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-01-29T17:21:45Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-01-29T17:21:45Z"]},{"key":"dc:date.issued","label":"Date","values":["2025"]},{"key":"dc:type","label":"Dc Type","values":["Dissertation/Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer Sciences"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://repository.upenn.edu/handle/20.500.14332/62344"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["2025"]},{"key":"dc:description.abstract","label":"Abstract","values":["Black-box optimization is a general framework for problems where our goal is to find an input that maximizes some real-valued objective function. Typically, no mathematical form is available for this objective function, and it may be expensive to evaluate, making it a black-box. Many practical scientific discovery problems can be framed as black-box optimization. For example, in drug discovery one might seek to design a small molecule that maximizes a real-valued objective function, such as predicted therapeutic activity against a target pathogen. Such objectives lack closed-form expressions and may require costly physics-based simulations or laboratory experiments to evaluate, motivating sample-efficient optimization methods. Bayesian optimization (BO) is a widely used machine learning method for sample-efficient black-box optimization. However, standard BO methods assume a continuous, numerical input space and are not directly applicable to structured, discrete domains such as molecules or proteins. Latent space Bayesian optimization (LS-BO) is a newly emerging approach for this setting. LS-BO employs generative models to embed discrete, structured inputs into continuous latent spaces where BO techniques can be applied. This dissertation presents recent work that advances LS-BO, enabling more effective optimization of challenging real-world objectives in scientific discovery. In addition, it extends the LS-BO framework to new problem settings that broaden its applicability and better align with the practical needs of scientific practitioners."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Doctor of Philosophy (PhD)"]},{"key":"dc:title","label":"Title","values":["Generative Bayesian Optimization for Structured Design"]}]}],"canonical_facts":{"dc:contributor.advisor":["Gardner, Jacob, R"],"dc:creator":["Maus, Natalie"],"dc:date.accessioned":["2026-01-29T17:21:45Z"],"dc:date.available":["2026-01-29T17:21:45Z"],"dc:date.issued":["2025"],"dc:description":["2025"],"dc:description.abstract":["Black-box optimization is a general framework for problems where our goal is to find an input that maximizes some real-valued objective function. Typically, no mathematical form is available for this objective function, and it may be expensive to evaluate, making it a black-box. Many practical scientific discovery problems can be framed as black-box optimization. For example, in drug discovery one might seek to design a small molecule that maximizes a real-valued objective function, such as predicted therapeutic activity against a target pathogen. Such objectives lack closed-form expressions and may require costly physics-based simulations or laboratory experiments to evaluate, motivating sample-efficient optimization methods. Bayesian optimization (BO) is a widely used machine learning method for sample-efficient black-box optimization. However, standard BO methods assume a continuous, numerical input space and are not directly applicable to structured, discrete domains such as molecules or proteins. Latent space Bayesian optimization (LS-BO) is a newly emerging approach for this setting. LS-BO employs generative models to embed discrete, structured inputs into continuous latent spaces where BO techniques can be applied. This dissertation presents recent work that advances LS-BO, enabling more effective optimization of challenging real-world objectives in scientific discovery. In addition, it extends the LS-BO framework to new problem settings that broaden its applicability and better align with the practical needs of scientific practitioners."],"dc:description.degree":["Doctor of Philosophy (PhD)"],"dc:identifier.uri":["https://repository.upenn.edu/handle/20.500.14332/62344"],"dc:language.iso":["en"],"dc:subject":["Computer Sciences"],"dc:title":["Generative Bayesian Optimization for Structured Design"],"dc:type":["Dissertation/Thesis"]},"updated_at":"2026-07-24T03:47:51Z"}