{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IMKAHJ6J47PWOQISJQJTHF7KVR","short_pith_number":"pith:IMKAHJ6J","schema_version":"1.0","canonical_sha256":"431403a7c9e7df6741124c133397eaac64835cc6b77ee5ba1bdbd46e1b701426","source":{"kind":"arxiv","id":"2505.24737","version":1},"attestation_state":"computed","paper":{"title":"Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Erchi Wang, Yuqing Zhu, Yu-Xiang Wang","submitted_at":"2025-05-30T15:56:58Z","abstract_excerpt":"This paper studies the problem of differentially private empirical risk minimization (DP-ERM) for binary linear classification. We obtain an efficient $(\\varepsilon,\\delta)$-DP algorithm with an empirical zero-one risk bound of $\\tilde{O}\\left(\\frac{1}{\\gamma^2\\varepsilon n} + \\frac{|S_{\\mathrm{out}}|}{\\gamma n}\\right)$ where $n$ is the number of data points, $S_{\\mathrm{out}}$ is an arbitrary subset of data one can remove and $\\gamma$ is the margin of linear separation of the remaining data points (after $S_{\\mathrm{out}}$ is removed). Here, $\\tilde{O}(\\cdot)$ hides only logarithmic terms. In"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.24737","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T15:56:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"75db7711f743b992a292a3b27cf40c9de29a38ce9bd297f621d6f676db246993","abstract_canon_sha256":"428df02cc3a20f10ea84c361a044f1b4daf1f1eb4c7a308689a571c1a2244131"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:55.801361Z","signature_b64":"1ZJ61IkIJkp6U2qmOjpyhJOG26A/w5AG+cmNpiVZHyLS6iSbyM1q1ZqThm/dqKlrH78mcoKDZrC2eXKDccKoBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"431403a7c9e7df6741124c133397eaac64835cc6b77ee5ba1bdbd46e1b701426","last_reissued_at":"2026-07-05T11:12:55.800757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:55.800757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Erchi Wang, Yuqing Zhu, Yu-Xiang Wang","submitted_at":"2025-05-30T15:56:58Z","abstract_excerpt":"This paper studies the problem of differentially private empirical risk minimization (DP-ERM) for binary linear classification. We obtain an efficient $(\\varepsilon,\\delta)$-DP algorithm with an empirical zero-one risk bound of $\\tilde{O}\\left(\\frac{1}{\\gamma^2\\varepsilon n} + \\frac{|S_{\\mathrm{out}}|}{\\gamma n}\\right)$ where $n$ is the number of data points, $S_{\\mathrm{out}}$ is an arbitrary subset of data one can remove and $\\gamma$ is the margin of linear separation of the remaining data points (after $S_{\\mathrm{out}}$ is removed). Here, $\\tilde{O}(\\cdot)$ hides only logarithmic terms. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24737","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.24737/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.24737","created_at":"2026-07-05T11:12:55.800828+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24737v1","created_at":"2026-07-05T11:12:55.800828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24737","created_at":"2026-07-05T11:12:55.800828+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMKAHJ6J47PW","created_at":"2026-07-05T11:12:55.800828+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMKAHJ6J47PWOQIS","created_at":"2026-07-05T11:12:55.800828+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMKAHJ6J","created_at":"2026-07-05T11:12:55.800828+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IMKAHJ6J47PWOQISJQJTHF7KVR","json":"https://pith.science/pith/IMKAHJ6J47PWOQISJQJTHF7KVR.json","graph_json":"https://pith.science/api/pith-number/IMKAHJ6J47PWOQISJQJTHF7KVR/graph.json","events_json":"https://pith.science/api/pith-number/IMKAHJ6J47PWOQISJQJTHF7KVR/events.json","paper":"https://pith.science/paper/IMKAHJ6J"},"agent_actions":{"view_html":"https://pith.science/pith/IMKAHJ6J47PWOQISJQJTHF7KVR","download_json":"https://pith.science/pith/IMKAHJ6J47PWOQISJQJTHF7KVR.json","view_paper":"https://pith.science/paper/IMKAHJ6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24737&json=true","fetch_graph":"https://pith.science/api/pith-number/IMKAHJ6J47PWOQISJQJTHF7KVR/graph.json","fetch_events":"https://pith.science/api/pith-number/IMKAHJ6J47PWOQISJQJTHF7KVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMKAHJ6J47PWOQISJQJTHF7KVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMKAHJ6J47PWOQISJQJTHF7KVR/action/storage_attestation","attest_author":"https://pith.science/pith/IMKAHJ6J47PWOQISJQJTHF7KVR/action/author_attestation","sign_citation":"https://pith.science/pith/IMKAHJ6J47PWOQISJQJTHF7KVR/action/citation_signature","submit_replication":"https://pith.science/pith/IMKAHJ6J47PWOQISJQJTHF7KVR/action/replication_record"}},"created_at":"2026-07-05T11:12:55.800828+00:00","updated_at":"2026-07-05T11:12:55.800828+00:00"}