{"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/quality-weighted-vendi-scores-and-their","title":"Quality-Weighted Vendi Scores And Their Application To Diverse Experimental Design","arxiv_id":"2405.02449","date":"2024-05-03","proceeding":null,"authors":["Quan Nguyen","Adji Bousso Dieng"],"abstract":"Experimental design techniques such as active search and Bayesian optimization are widely used in the natural sciences for data collection and discovery. However, existing techniques tend to favor exploitation over exploration of the search space, which causes them to get stuck in local optima. This ``collapse\" problem prevents experimental design algorithms from yielding diverse high-quality data. In this paper, we extend the Vendi scores -- a family of interpretable similarity-based diversity metrics -- to account for quality. We then leverage these quality-weighted Vendi scores to tackle experimental design problems across various applications, including drug discovery, materials discovery, and reinforcement learning. We found that quality-weighted Vendi scores allow us to construct policies for experimental design that flexibly balance quality and diversity, and ultimately assemble rich and diverse sets of high-performing data points. Our algorithms led to a 70%-170% increase in the number of effective discoveries compared to baselines.","url_abs":"https://arxiv.org/abs/2405.02449v1","url_pdf":"https://arxiv.org/pdf/2405.02449v1.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":"quality-weighted-vendi-scores-and-their","repo_url":"https://github.com/vertaix/quality-weighted-vendi-score","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"bayesian-optimization","task_name":"Bayesian Optimization"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"drug-discovery","task_name":"Drug Discovery"},{"task_slug":"experimental-design","task_name":"Experimental Design"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.02449","atlas_url":"https://app.syntology.ai/?focus=2405.02449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.02449"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vertaix/quality-weighted-vendi-score","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ad73c9e8d0084d32","entry":"entropy_q","repo":"vertaix/quality-weighted-vendi-score","repo_kind":"official","path":"diverse_search/utils.py","file_url":"https://github.com/vertaix/quality-weighted-vendi-score/blob/HEAD/diverse_search/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ad73c9e8d0084d32"}},{"code_sha256_prefix":"0037210780a90b14","entry":"generate_batch","repo":"vertaix/quality-weighted-vendi-score","repo_kind":"official","path":"diverse_bayesopt/robot/trust_region.py","file_url":"https://github.com/vertaix/quality-weighted-vendi-score/blob/HEAD/diverse_bayesopt/robot/trust_region.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0037210780a90b14"}},{"code_sha256_prefix":"1464b529337ba246","entry":"get_fantasy_label","repo":"vertaix/quality-weighted-vendi-score","repo_kind":"official","path":"diverse_search/utils.py","file_url":"https://github.com/vertaix/quality-weighted-vendi-score/blob/HEAD/diverse_search/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1464b529337ba246"}},{"code_sha256_prefix":"9027e63704fb660a","entry":"tiebreak_max","repo":"vertaix/quality-weighted-vendi-score","repo_kind":"official","path":"diverse_search/utils.py","file_url":"https://github.com/vertaix/quality-weighted-vendi-score/blob/HEAD/diverse_search/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9027e63704fb660a"}},{"code_sha256_prefix":"b84597ee45a5c18a","entry":"update_models_end_to_end","repo":"vertaix/quality-weighted-vendi-score","repo_kind":"official","path":"diverse_bayesopt/robot/gp_utils/update_models.py","file_url":"https://github.com/vertaix/quality-weighted-vendi-score/blob/HEAD/diverse_bayesopt/robot/gp_utils/update_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b84597ee45a5c18a"}},{"code_sha256_prefix":"bff6178af0ea9688","entry":"update_surr_model","repo":"vertaix/quality-weighted-vendi-score","repo_kind":"official","path":"diverse_bayesopt/robot/gp_utils/update_models.py","file_url":"https://github.com/vertaix/quality-weighted-vendi-score/blob/HEAD/diverse_bayesopt/robot/gp_utils/update_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bff6178af0ea9688"}},{"code_sha256_prefix":"5a37bfb90b322cff","entry":"append_gram_matrix","repo":"vertaix/quality-weighted-vendi-score","repo_kind":"official","path":"diverse_bayesopt/robot/robot.py","file_url":"https://github.com/vertaix/quality-weighted-vendi-score/blob/HEAD/diverse_bayesopt/robot/robot.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a37bfb90b322cff"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}