{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NFLC3CWCKP6YUKKGLGLREQSVDO","short_pith_number":"pith:NFLC3CWC","schema_version":"1.0","canonical_sha256":"69562d8ac253fd8a294659971242551b99f2cb5e9622f268347fd42c8005f049","source":{"kind":"arxiv","id":"1912.06508","version":1},"attestation_state":"computed","paper":{"title":"A Distributed Quasi-Newton Algorithm for Primal and Dual Regularized Empirical Risk Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ching-pei Lee, Cong Han Lim, Stephen J. Wright","submitted_at":"2019-12-12T18:25:37Z","abstract_excerpt":"We propose a communication- and computation-efficient distributed optimization algorithm using second-order information for solving empirical risk minimization (ERM) problems with a nonsmooth regularization term. Our algorithm is applicable to both the primal and the dual ERM problem. Current second-order and quasi-Newton methods for this problem either do not work well in the distributed setting or work only for specific regularizers. Our algorithm uses successive quadratic approximations of the smooth part, and we describe how to maintain an approximation of the (generalized) Hessian and sol"},"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":"1912.06508","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-12T18:25:37Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"dd61e567d3d0f4adcf27bcda975563120c9eec38864f6e2c967458fafd3ba079","abstract_canon_sha256":"cc458729eed5e3fd389ac65ea970054bffdfea93710c91f705dd13f7f63b1067"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:26:01.799909Z","signature_b64":"ObrkBTJXyhmtajaZuK30tqkhKTUB7c1zYHhyVsCHi1z+3iSapZMXNi8rBXvhKi4upiYNdbCZZ4EyX/zTe7RlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69562d8ac253fd8a294659971242551b99f2cb5e9622f268347fd42c8005f049","last_reissued_at":"2026-07-05T00:26:01.799503Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:26:01.799503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Distributed Quasi-Newton Algorithm for Primal and Dual Regularized Empirical Risk Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ching-pei Lee, Cong Han Lim, Stephen J. Wright","submitted_at":"2019-12-12T18:25:37Z","abstract_excerpt":"We propose a communication- and computation-efficient distributed optimization algorithm using second-order information for solving empirical risk minimization (ERM) problems with a nonsmooth regularization term. Our algorithm is applicable to both the primal and the dual ERM problem. Current second-order and quasi-Newton methods for this problem either do not work well in the distributed setting or work only for specific regularizers. Our algorithm uses successive quadratic approximations of the smooth part, and we describe how to maintain an approximation of the (generalized) Hessian and sol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.06508","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/1912.06508/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":"1912.06508","created_at":"2026-07-05T00:26:01.799561+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.06508v1","created_at":"2026-07-05T00:26:01.799561+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.06508","created_at":"2026-07-05T00:26:01.799561+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFLC3CWCKP6Y","created_at":"2026-07-05T00:26:01.799561+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFLC3CWCKP6YUKKG","created_at":"2026-07-05T00:26:01.799561+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFLC3CWC","created_at":"2026-07-05T00:26:01.799561+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/NFLC3CWCKP6YUKKGLGLREQSVDO","json":"https://pith.science/pith/NFLC3CWCKP6YUKKGLGLREQSVDO.json","graph_json":"https://pith.science/api/pith-number/NFLC3CWCKP6YUKKGLGLREQSVDO/graph.json","events_json":"https://pith.science/api/pith-number/NFLC3CWCKP6YUKKGLGLREQSVDO/events.json","paper":"https://pith.science/paper/NFLC3CWC"},"agent_actions":{"view_html":"https://pith.science/pith/NFLC3CWCKP6YUKKGLGLREQSVDO","download_json":"https://pith.science/pith/NFLC3CWCKP6YUKKGLGLREQSVDO.json","view_paper":"https://pith.science/paper/NFLC3CWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.06508&json=true","fetch_graph":"https://pith.science/api/pith-number/NFLC3CWCKP6YUKKGLGLREQSVDO/graph.json","fetch_events":"https://pith.science/api/pith-number/NFLC3CWCKP6YUKKGLGLREQSVDO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFLC3CWCKP6YUKKGLGLREQSVDO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFLC3CWCKP6YUKKGLGLREQSVDO/action/storage_attestation","attest_author":"https://pith.science/pith/NFLC3CWCKP6YUKKGLGLREQSVDO/action/author_attestation","sign_citation":"https://pith.science/pith/NFLC3CWCKP6YUKKGLGLREQSVDO/action/citation_signature","submit_replication":"https://pith.science/pith/NFLC3CWCKP6YUKKGLGLREQSVDO/action/replication_record"}},"created_at":"2026-07-05T00:26:01.799561+00:00","updated_at":"2026-07-05T00:26:01.799561+00:00"}