{"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/accuracy-first-selecting-a-differential-1","title":"Accuracy First: Selecting a Differential Privacy Level for Accuracy-Constrained ERM","arxiv_id":"1705.10829","date":"2017-05-30","proceeding":null,"authors":["Katrina Ligett","Seth Neel","Aaron Roth","Bo Waggoner","Z. Steven Wu"],"abstract":"Traditional approaches to differential privacy assume a fixed privacy\nrequirement $\\epsilon$ for a computation, and attempt to maximize the accuracy\nof the computation subject to the privacy constraint. As differential privacy\nis increasingly deployed in practical settings, it may often be that there is\ninstead a fixed accuracy requirement for a given computation and the data\nanalyst would like to maximize the privacy of the computation subject to the\naccuracy constraint. This raises the question of how to find and run a\nmaximally private empirical risk minimizer subject to a given accuracy\nrequirement. We propose a general \"noise reduction\" framework that can apply to\na variety of private empirical risk minimization (ERM) algorithms, using them\nto \"search\" the space of privacy levels to find the empirically strongest one\nthat meets the accuracy constraint, incurring only logarithmic overhead in the\nnumber of privacy levels searched. The privacy analysis of our algorithm leads\nnaturally to a version of differential privacy where the privacy parameters are\ndependent on the data, which we term ex-post privacy, and which is related to\nthe recently introduced notion of privacy odometers. We also give an ex-post\nprivacy analysis of the classical AboveThreshold privacy tool, modifying it to\nallow for queries chosen depending on the database. Finally, we apply our\napproach to two common objectives, regularized linear and logistic regression,\nand empirically compare our noise reduction methods to (i) inverting the\ntheoretical utility guarantees of standard private ERM algorithms and (ii) a\nstronger, empirical baseline based on binary search.","url_abs":"http://arxiv.org/abs/1705.10829v1","url_pdf":"http://arxiv.org/pdf/1705.10829v1.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":"accuracy-first-selecting-a-differential-1","repo_url":"https://github.com/steven7woo/Accuracy-First-Differential-Privacy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.10829","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.10829"}},"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/steven7woo/Accuracy-First-Differential-Privacy","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"ran":2,"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":"2a4d1e9ba874e0d2","entry":"parse_inputs","repo":"steven7woo/Accuracy-First-Differential-Privacy","repo_kind":"listed","path":"code/run_logist.py","file_url":"https://github.com/steven7woo/Accuracy-First-Differential-Privacy/blob/HEAD/code/run_logist.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a4d1e9ba874e0d2"}},{"code_sha256_prefix":"80f0aa50ad0ee664","entry":"stringify","repo":"steven7woo/Accuracy-First-Differential-Privacy","repo_kind":"listed","path":"code/run_ridge.py","file_url":"https://github.com/steven7woo/Accuracy-First-Differential-Privacy/blob/HEAD/code/run_ridge.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"80f0aa50ad0ee664"}},{"code_sha256_prefix":"6c2d6a017c68975a","entry":"parse_inputs","repo":"steven7woo/Accuracy-First-Differential-Privacy","repo_kind":"listed","path":"code/run_ridge.py","file_url":"https://github.com/steven7woo/Accuracy-First-Differential-Privacy/blob/HEAD/code/run_ridge.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":"6c2d6a017c68975a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}