{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:6R6ZJCJ2F6PSZLU62EXAHV7DPZ","short_pith_number":"pith:6R6ZJCJ2","schema_version":"1.0","canonical_sha256":"f47d94893a2f9f2cae9ed12e03d7e37e46e3feccdca6ac92477070c88946e636","source":{"kind":"arxiv","id":"1706.08344","version":3},"attestation_state":"computed","paper":{"title":"High-dimensional classification by sparse logistic regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Felix Abramovich, Vadim Grinshtein","submitted_at":"2017-06-26T12:42:42Z","abstract_excerpt":"We consider high-dimensional binary classification by sparse logistic regression. We propose a model/feature selection procedure based on penalized maximum likelihood with a complexity penalty on the model size and derive the non-asymptotic bounds for the resulting misclassification excess risk. The bounds can be reduced under the additional low-noise condition. The proposed complexity penalty is remarkably related to the VC-dimension of a set of sparse linear classifiers. Implementation of any complexity penalty-based criterion, however, requires a combinatorial search over all possible model"},"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":"1706.08344","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2017-06-26T12:42:42Z","cross_cats_sorted":["stat.ML","stat.TH"],"title_canon_sha256":"4df39eda1b0e65cf8c9223896a6df07ff47f7eb264014dd5675aeab297b1eab9","abstract_canon_sha256":"6c1f4f2f9f889a47ac0e85712ddbd85ec8fd817c305adf84857ec80c42e380ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:31.062491Z","signature_b64":"ceGUb9M6xhbauAkomcMHreOeSzuUyn1cPfHWCt74n0nZCQ8rFe2//k+kdJv8tN6+4v6OvTXEq4aalAwjzk8lBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f47d94893a2f9f2cae9ed12e03d7e37e46e3feccdca6ac92477070c88946e636","last_reissued_at":"2026-05-18T00:00:31.061930Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:31.061930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-dimensional classification by sparse logistic regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Felix Abramovich, Vadim Grinshtein","submitted_at":"2017-06-26T12:42:42Z","abstract_excerpt":"We consider high-dimensional binary classification by sparse logistic regression. We propose a model/feature selection procedure based on penalized maximum likelihood with a complexity penalty on the model size and derive the non-asymptotic bounds for the resulting misclassification excess risk. The bounds can be reduced under the additional low-noise condition. The proposed complexity penalty is remarkably related to the VC-dimension of a set of sparse linear classifiers. Implementation of any complexity penalty-based criterion, however, requires a combinatorial search over all possible model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.08344","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1706.08344","created_at":"2026-05-18T00:00:31.062016+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.08344v3","created_at":"2026-05-18T00:00:31.062016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.08344","created_at":"2026-05-18T00:00:31.062016+00:00"},{"alias_kind":"pith_short_12","alias_value":"6R6ZJCJ2F6PS","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"6R6ZJCJ2F6PSZLU6","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"6R6ZJCJ2","created_at":"2026-05-18T12:31:03.183658+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/6R6ZJCJ2F6PSZLU62EXAHV7DPZ","json":"https://pith.science/pith/6R6ZJCJ2F6PSZLU62EXAHV7DPZ.json","graph_json":"https://pith.science/api/pith-number/6R6ZJCJ2F6PSZLU62EXAHV7DPZ/graph.json","events_json":"https://pith.science/api/pith-number/6R6ZJCJ2F6PSZLU62EXAHV7DPZ/events.json","paper":"https://pith.science/paper/6R6ZJCJ2"},"agent_actions":{"view_html":"https://pith.science/pith/6R6ZJCJ2F6PSZLU62EXAHV7DPZ","download_json":"https://pith.science/pith/6R6ZJCJ2F6PSZLU62EXAHV7DPZ.json","view_paper":"https://pith.science/paper/6R6ZJCJ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.08344&json=true","fetch_graph":"https://pith.science/api/pith-number/6R6ZJCJ2F6PSZLU62EXAHV7DPZ/graph.json","fetch_events":"https://pith.science/api/pith-number/6R6ZJCJ2F6PSZLU62EXAHV7DPZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6R6ZJCJ2F6PSZLU62EXAHV7DPZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6R6ZJCJ2F6PSZLU62EXAHV7DPZ/action/storage_attestation","attest_author":"https://pith.science/pith/6R6ZJCJ2F6PSZLU62EXAHV7DPZ/action/author_attestation","sign_citation":"https://pith.science/pith/6R6ZJCJ2F6PSZLU62EXAHV7DPZ/action/citation_signature","submit_replication":"https://pith.science/pith/6R6ZJCJ2F6PSZLU62EXAHV7DPZ/action/replication_record"}},"created_at":"2026-05-18T00:00:31.062016+00:00","updated_at":"2026-05-18T00:00:31.062016+00:00"}