{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XS4IJC5QZHQU3PJHPFALYULXHA","short_pith_number":"pith:XS4IJC5Q","schema_version":"1.0","canonical_sha256":"bcb8848bb0c9e14dbd277940bc5177380c04f10a9baec7cb2d4619e895872b7d","source":{"kind":"arxiv","id":"1905.10874","version":2},"attestation_state":"computed","paper":{"title":"RSN: Randomized Subspace Newton","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Dmitry Kovalev, Felix Lieder, Peter Richt\\'arik, Robert M. Gower","submitted_at":"2019-05-26T20:33:51Z","abstract_excerpt":"We develop a randomized Newton method capable of solving learning problems with huge dimensional feature spaces, which is a common setting in applications such as medical imaging, genomics and seismology. Our method leverages randomized sketching in a new way, by finding the Newton direction constrained to the space spanned by a random sketch. We develop a simple global linear convergence theory that holds for practically all sketching techniques, which gives the practitioners the freedom to design custom sketching approaches suitable for particular applications. We perform numerical experimen"},"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":"1905.10874","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-05-26T20:33:51Z","cross_cats_sorted":[],"title_canon_sha256":"8cf50120886d63c658ce6a3913e9501cda6f2dff7692587e10ae497638ba4ec1","abstract_canon_sha256":"f536feb4f6713f1a9103bffe309d93576d2fa67e5fa2b7de4e6055994f6fd55d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:09:25.767499Z","signature_b64":"ZcHHIzkUnzILpjuxt9UxP1c1OmV6kMFhPGaOlKoege6ORSLyEMzRJayEMiz1m7rGh3WWZDywdSQSBPHRuw7UBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcb8848bb0c9e14dbd277940bc5177380c04f10a9baec7cb2d4619e895872b7d","last_reissued_at":"2026-07-05T00:09:25.767084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:09:25.767084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RSN: Randomized Subspace Newton","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Dmitry Kovalev, Felix Lieder, Peter Richt\\'arik, Robert M. Gower","submitted_at":"2019-05-26T20:33:51Z","abstract_excerpt":"We develop a randomized Newton method capable of solving learning problems with huge dimensional feature spaces, which is a common setting in applications such as medical imaging, genomics and seismology. Our method leverages randomized sketching in a new way, by finding the Newton direction constrained to the space spanned by a random sketch. We develop a simple global linear convergence theory that holds for practically all sketching techniques, which gives the practitioners the freedom to design custom sketching approaches suitable for particular applications. We perform numerical experimen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10874","kind":"arxiv","version":2},"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/1905.10874/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":"1905.10874","created_at":"2026-07-05T00:09:25.767141+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.10874v2","created_at":"2026-07-05T00:09:25.767141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10874","created_at":"2026-07-05T00:09:25.767141+00:00"},{"alias_kind":"pith_short_12","alias_value":"XS4IJC5QZHQU","created_at":"2026-07-05T00:09:25.767141+00:00"},{"alias_kind":"pith_short_16","alias_value":"XS4IJC5QZHQU3PJH","created_at":"2026-07-05T00:09:25.767141+00:00"},{"alias_kind":"pith_short_8","alias_value":"XS4IJC5Q","created_at":"2026-07-05T00:09:25.767141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08256","citing_title":"Model-Driven Subspaces for Large-Scale Optimization with Local Approximation Strategy","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XS4IJC5QZHQU3PJHPFALYULXHA","json":"https://pith.science/pith/XS4IJC5QZHQU3PJHPFALYULXHA.json","graph_json":"https://pith.science/api/pith-number/XS4IJC5QZHQU3PJHPFALYULXHA/graph.json","events_json":"https://pith.science/api/pith-number/XS4IJC5QZHQU3PJHPFALYULXHA/events.json","paper":"https://pith.science/paper/XS4IJC5Q"},"agent_actions":{"view_html":"https://pith.science/pith/XS4IJC5QZHQU3PJHPFALYULXHA","download_json":"https://pith.science/pith/XS4IJC5QZHQU3PJHPFALYULXHA.json","view_paper":"https://pith.science/paper/XS4IJC5Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.10874&json=true","fetch_graph":"https://pith.science/api/pith-number/XS4IJC5QZHQU3PJHPFALYULXHA/graph.json","fetch_events":"https://pith.science/api/pith-number/XS4IJC5QZHQU3PJHPFALYULXHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XS4IJC5QZHQU3PJHPFALYULXHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XS4IJC5QZHQU3PJHPFALYULXHA/action/storage_attestation","attest_author":"https://pith.science/pith/XS4IJC5QZHQU3PJHPFALYULXHA/action/author_attestation","sign_citation":"https://pith.science/pith/XS4IJC5QZHQU3PJHPFALYULXHA/action/citation_signature","submit_replication":"https://pith.science/pith/XS4IJC5QZHQU3PJHPFALYULXHA/action/replication_record"}},"created_at":"2026-07-05T00:09:25.767141+00:00","updated_at":"2026-07-05T00:09:25.767141+00:00"}