{"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/joint-selection-adaptively-incorporating","title":"Joint Selection: Adaptively Incorporating Public Information for Private Synthetic Data","arxiv_id":"2403.07797","date":"2024-03-12","proceeding":null,"authors":["Miguel Fuentes","Brett Mullins","Ryan McKenna","Gerome Miklau","Daniel Sheldon"],"abstract":"Mechanisms for generating differentially private synthetic data based on marginals and graphical models have been successful in a wide range of settings. However, one limitation of these methods is their inability to incorporate public data. Initializing a data generating model by pre-training on public data has shown to improve the quality of synthetic data, but this technique is not applicable when model structure is not determined a priori. We develop the mechanism jam-pgm, which expands the adaptive measurements framework to jointly select between measuring public data and private data. This technique allows for public data to be included in a graphical-model-based mechanism. We show that jam-pgm is able to outperform both publicly assisted and non publicly assisted synthetic data generation mechanisms even when the public data distribution is biased.","url_abs":"https://arxiv.org/abs/2403.07797v1","url_pdf":"https://arxiv.org/pdf/2403.07797v1.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":"joint-selection-adaptively-incorporating","repo_url":"https://github.com/miguel-fuentes/jam_aistats","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"synthetic-data-generation","task_name":"Synthetic Data Generation"}],"methods":[{"method_slug":"non","method_name":"NON"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.07797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07797"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/miguel-fuentes/jam_aistats","reach":{"status":"ok"}}],"summary":{"ran":11,"ran_honours":1},"by_repo_kind":{"official":{"samples":12,"ran":12,"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":12,"samples":[{"code_sha256_prefix":"12513a27a1865536","entry":"cdp_delta","repo":"miguel-fuentes/jam_aistats","repo_kind":"official","path":"code/mechanisms/cdp2adp.py","file_url":"https://github.com/miguel-fuentes/jam_aistats/blob/HEAD/code/mechanisms/cdp2adp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"12513a27a1865536"}},{"code_sha256_prefix":"6026d9da4638c121","entry":"cdp_delta_standard","repo":"miguel-fuentes/jam_aistats","repo_kind":"official","path":"code/mechanisms/cdp2adp.py","file_url":"https://github.com/miguel-fuentes/jam_aistats/blob/HEAD/code/mechanisms/cdp2adp.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6026d9da4638c121"}},{"code_sha256_prefix":"438c48170078d9e5","entry":"cdp_eps","repo":"miguel-fuentes/jam_aistats","repo_kind":"official","path":"code/mechanisms/cdp2adp.py","file_url":"https://github.com/miguel-fuentes/jam_aistats/blob/HEAD/code/mechanisms/cdp2adp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"438c48170078d9e5"}},{"code_sha256_prefix":"15f16fae09db2759","entry":"convert_back","repo":"miguel-fuentes/jam_aistats","repo_kind":"official","path":"code/mechanisms/hdmm+appgm.py","file_url":"https://github.com/miguel-fuentes/jam_aistats/blob/HEAD/code/mechanisms/hdmm%2Bappgm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"15f16fae09db2759"}},{"code_sha256_prefix":"e519bd15e017a877","entry":"downward_closure","repo":"miguel-fuentes/jam_aistats","repo_kind":"official","path":"code/mechanisms/adaptive_grid.py","file_url":"https://github.com/miguel-fuentes/jam_aistats/blob/HEAD/code/mechanisms/adaptive_grid.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e519bd15e017a877"}},{"code_sha256_prefix":"ef1ef33de7a9f882","entry":"downward_closure","repo":"miguel-fuentes/jam_aistats","repo_kind":"official","path":"code/mechanisms/aim.py","file_url":"https://github.com/miguel-fuentes/jam_aistats/blob/HEAD/code/mechanisms/aim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ef1ef33de7a9f882"}},{"code_sha256_prefix":"a0f36b2b02e60d5c","entry":"generalized_em_scores","repo":"miguel-fuentes/jam_aistats","repo_kind":"official","path":"code/mechanisms/mechanism.py","file_url":"https://github.com/miguel-fuentes/jam_aistats/blob/HEAD/code/mechanisms/mechanism.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a0f36b2b02e60d5c"}},{"code_sha256_prefix":"e12535051bbf7d6d","entry":"measure","repo":"miguel-fuentes/jam_aistats","repo_kind":"official","path":"code/mechanisms/mst.py","file_url":"https://github.com/miguel-fuentes/jam_aistats/blob/HEAD/code/mechanisms/mst.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e12535051bbf7d6d"}},{"code_sha256_prefix":"87f72fb6f142740c","entry":"pareto_efficient","repo":"miguel-fuentes/jam_aistats","repo_kind":"official","path":"code/mechanisms/mechanism.py","file_url":"https://github.com/miguel-fuentes/jam_aistats/blob/HEAD/code/mechanisms/mechanism.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"87f72fb6f142740c"}},{"code_sha256_prefix":"7ab9a745dded1630","entry":"powerset","repo":"miguel-fuentes/jam_aistats","repo_kind":"official","path":"code/mechanisms/adaptive_grid.py","file_url":"https://github.com/miguel-fuentes/jam_aistats/blob/HEAD/code/mechanisms/adaptive_grid.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7ab9a745dded1630"}},{"code_sha256_prefix":"802df9e4d1beab55","entry":"powerset","repo":"miguel-fuentes/jam_aistats","repo_kind":"official","path":"code/mechanisms/aim.py","file_url":"https://github.com/miguel-fuentes/jam_aistats/blob/HEAD/code/mechanisms/aim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"802df9e4d1beab55"}},{"code_sha256_prefix":"491c48108d39e94c","entry":"worst_approximated","repo":"miguel-fuentes/jam_aistats","repo_kind":"official","path":"code/mechanisms/mwem+pgm.py","file_url":"https://github.com/miguel-fuentes/jam_aistats/blob/HEAD/code/mechanisms/mwem%2Bpgm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"491c48108d39e94c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}