{"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/sample-efficient-optimization-in-the-latent","title":"Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining","arxiv_id":"2006.09191","date":"2020-06-16","proceeding":"NeurIPS 2020 12","authors":["Austin Tripp","Erik Daxberger","José Miguel Hernández-Lobato"],"abstract":"Many important problems in science and engineering, such as drug design, involve optimizing an expensive black-box objective function over a complex, high-dimensional, and structured input space. Although machine learning techniques have shown promise in solving such problems, existing approaches substantially lack sample efficiency. We introduce an improved method for efficient black-box optimization, which performs the optimization in the low-dimensional, continuous latent manifold learned by a deep generative model. In contrast to previous approaches, we actively steer the generative model to maintain a latent manifold that is highly useful for efficiently optimizing the objective. We achieve this by periodically retraining the generative model on the data points queried along the optimization trajectory, as well as weighting those data points according to their objective function value. This weighted retraining can be easily implemented on top of existing methods, and is empirically shown to significantly improve their efficiency and performance on synthetic and real-world optimization problems.","url_abs":"https://arxiv.org/abs/2006.09191v2","url_pdf":"https://arxiv.org/pdf/2006.09191v2.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":"sample-efficient-optimization-in-the-latent","repo_url":"https://github.com/cambridge-mlg/weighted-retraining","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"drug-design","task_name":"Drug Design"},{"task_slug":"molecular-graph-generation","task_name":"Molecular Graph Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.09191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.09191"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"deterministic:regex_extraction","url":"https://github.com/mkusner/grammarVAE","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/wengong-jin/icml18-jtnn","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cambridge-mlg/weighted-retraining","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":4},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1},"found_in_text":{"samples":1,"ran":0,"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":4,"samples":[{"code_sha256_prefix":"16eaf789c4a4401d","entry":"pop_or_nothing","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"16eaf789c4a4401d"}},{"code_sha256_prefix":"0bf41e0b28d9835c","entry":"prods_to_eq","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"0bf41e0b28d9835c"}},{"code_sha256_prefix":"cb40f0c69ca29671","entry":"ZincGrammarModel","repo":"mkusner/grammarVAE","repo_kind":"found_in_text","path":"molecule_vae.py","file_url":"https://github.com/mkusner/grammarVAE/blob/HEAD/molecule_vae.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb40f0c69ca29671"}},{"code_sha256_prefix":"bd5df031b64e57d3","entry":"get_zinc_tokenizer","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"bd5df031b64e57d3"}},{"code_sha256_prefix":"965c6ca9f6bdf6cb","entry":"gp_performance_metrics","repo":"cambridge-mlg/weighted-retraining","repo_kind":"official","path":"weighted_retraining/gp_train.py","file_url":"https://github.com/cambridge-mlg/weighted-retraining/blob/HEAD/weighted_retraining/gp_train.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":"965c6ca9f6bdf6cb"}},{"code_sha256_prefix":"b30f075b7653c03d","entry":"robust_multi_restart_optimizer","repo":"cambridge-mlg/weighted-retraining","repo_kind":"official","path":"weighted_retraining/gp_opt.py","file_url":"https://github.com/cambridge-mlg/weighted-retraining/blob/HEAD/weighted_retraining/gp_opt.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":"b30f075b7653c03d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}