{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JT4PFRPWIJOCKZR45VEWERTJBT","short_pith_number":"pith:JT4PFRPW","schema_version":"1.0","canonical_sha256":"4cf8f2c5f6425c25663ced496246690ceb8fd94f5f0f8c43a4225d1187df9769","source":{"kind":"arxiv","id":"2207.08171","version":1},"attestation_state":"computed","paper":{"title":"SP2: A Second Order Stochastic Polyak Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Deanna Needell, Martin Tak\\'a\\v{c}, Robert M. Gower, Shuang Li, William J. Swartworth","submitted_at":"2022-07-17T13:25:58Z","abstract_excerpt":"Recently the \"SP\" (Stochastic Polyak step size) method has emerged as a competitive adaptive method for setting the step sizes of SGD. SP can be interpreted as a method specialized to interpolated models, since it solves the interpolation equations. SP solves these equation by using local linearizations of the model. We take a step further and develop a method for solving the interpolation equations that uses the local second-order approximation of the model. Our resulting method SP2 uses Hessian-vector products to speed-up the convergence of SP. Furthermore, and rather uniquely among second-o"},"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":"2207.08171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-17T13:25:58Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"ef0c99f0fc702a28ac15e9dcf26528e5bf5b7e0e80a8bfd060a30ffbcd4da0ec","abstract_canon_sha256":"5a4e2759a0db64307a2a5625e1ad7b8425afba99ef3491c44b0e04daa2387db3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:41:01.770236Z","signature_b64":"HZAabvfc2Wzx4Tgut0fQLcjBWM+z8rLtuFvKS8kAAv9SOmBv+cuQH25Rq27bFVgSKvfjUPXhZ+4/Z0loRBVQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cf8f2c5f6425c25663ced496246690ceb8fd94f5f0f8c43a4225d1187df9769","last_reissued_at":"2026-07-05T04:41:01.769874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:41:01.769874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SP2: A Second Order Stochastic Polyak Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Deanna Needell, Martin Tak\\'a\\v{c}, Robert M. Gower, Shuang Li, William J. Swartworth","submitted_at":"2022-07-17T13:25:58Z","abstract_excerpt":"Recently the \"SP\" (Stochastic Polyak step size) method has emerged as a competitive adaptive method for setting the step sizes of SGD. SP can be interpreted as a method specialized to interpolated models, since it solves the interpolation equations. SP solves these equation by using local linearizations of the model. We take a step further and develop a method for solving the interpolation equations that uses the local second-order approximation of the model. Our resulting method SP2 uses Hessian-vector products to speed-up the convergence of SP. Furthermore, and rather uniquely among second-o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.08171","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/2207.08171/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":"2207.08171","created_at":"2026-07-05T04:41:01.769937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.08171v1","created_at":"2026-07-05T04:41:01.769937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.08171","created_at":"2026-07-05T04:41:01.769937+00:00"},{"alias_kind":"pith_short_12","alias_value":"JT4PFRPWIJOC","created_at":"2026-07-05T04:41:01.769937+00:00"},{"alias_kind":"pith_short_16","alias_value":"JT4PFRPWIJOCKZR4","created_at":"2026-07-05T04:41:01.769937+00:00"},{"alias_kind":"pith_short_8","alias_value":"JT4PFRPW","created_at":"2026-07-05T04:41:01.769937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.15071","citing_title":"Enhancing Optimizer Stability: Momentum Adaptation of The NGN Step-size","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JT4PFRPWIJOCKZR45VEWERTJBT","json":"https://pith.science/pith/JT4PFRPWIJOCKZR45VEWERTJBT.json","graph_json":"https://pith.science/api/pith-number/JT4PFRPWIJOCKZR45VEWERTJBT/graph.json","events_json":"https://pith.science/api/pith-number/JT4PFRPWIJOCKZR45VEWERTJBT/events.json","paper":"https://pith.science/paper/JT4PFRPW"},"agent_actions":{"view_html":"https://pith.science/pith/JT4PFRPWIJOCKZR45VEWERTJBT","download_json":"https://pith.science/pith/JT4PFRPWIJOCKZR45VEWERTJBT.json","view_paper":"https://pith.science/paper/JT4PFRPW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.08171&json=true","fetch_graph":"https://pith.science/api/pith-number/JT4PFRPWIJOCKZR45VEWERTJBT/graph.json","fetch_events":"https://pith.science/api/pith-number/JT4PFRPWIJOCKZR45VEWERTJBT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JT4PFRPWIJOCKZR45VEWERTJBT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JT4PFRPWIJOCKZR45VEWERTJBT/action/storage_attestation","attest_author":"https://pith.science/pith/JT4PFRPWIJOCKZR45VEWERTJBT/action/author_attestation","sign_citation":"https://pith.science/pith/JT4PFRPWIJOCKZR45VEWERTJBT/action/citation_signature","submit_replication":"https://pith.science/pith/JT4PFRPWIJOCKZR45VEWERTJBT/action/replication_record"}},"created_at":"2026-07-05T04:41:01.769937+00:00","updated_at":"2026-07-05T04:41:01.769937+00:00"}