{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SBRLZJJ34RV47EYI3EL37MPMNW","short_pith_number":"pith:SBRLZJJ3","schema_version":"1.0","canonical_sha256":"9062bca53be46bcf9308d917bfb1ec6db5a8111823e687c93d143459eaaf45b1","source":{"kind":"arxiv","id":"2109.05198","version":1},"attestation_state":"computed","paper":{"title":"Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Majid Jahani, Martin Tak\\'a\\v{c}, Michael W. Mahoney, Peter Richt\\'arik, Sergey Rusakov, Zheng Shi","submitted_at":"2021-09-11T06:39:50Z","abstract_excerpt":"We present a novel adaptive optimization algorithm for large-scale machine learning problems. Equipped with a low-cost estimate of local curvature and Lipschitz smoothness, our method dynamically adapts the search direction and step-size. The search direction contains gradient information preconditioned by a well-scaled diagonal preconditioning matrix that captures the local curvature information. Our methodology does not require the tedious task of learning rate tuning, as the learning rate is updated automatically without adding an extra hyperparameter. We provide convergence guarantees on a"},"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":"2109.05198","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-11T06:39:50Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"a6ad272536f27db8e5cc57ce3a5eb00140267941afbe40485ed264de9b8a6f15","abstract_canon_sha256":"9cf949e1612eaa0ec08b18e27827c65c50ccfa10d5f7296d5888faa20410ee0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:36.169961Z","signature_b64":"z8JX1rXTtbATZ2E7Rkbmb2zbb9BVa+DyyH7qzlt8Q9SjWyKzK2xr+NzpO9eefTEM0a13rS0zvY06aZaUiyV7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9062bca53be46bcf9308d917bfb1ec6db5a8111823e687c93d143459eaaf45b1","last_reissued_at":"2026-07-05T03:13:36.169526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:36.169526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Majid Jahani, Martin Tak\\'a\\v{c}, Michael W. Mahoney, Peter Richt\\'arik, Sergey Rusakov, Zheng Shi","submitted_at":"2021-09-11T06:39:50Z","abstract_excerpt":"We present a novel adaptive optimization algorithm for large-scale machine learning problems. Equipped with a low-cost estimate of local curvature and Lipschitz smoothness, our method dynamically adapts the search direction and step-size. The search direction contains gradient information preconditioned by a well-scaled diagonal preconditioning matrix that captures the local curvature information. Our methodology does not require the tedious task of learning rate tuning, as the learning rate is updated automatically without adding an extra hyperparameter. We provide convergence guarantees on a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05198","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/2109.05198/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":"2109.05198","created_at":"2026-07-05T03:13:36.169581+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.05198v1","created_at":"2026-07-05T03:13:36.169581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05198","created_at":"2026-07-05T03:13:36.169581+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBRLZJJ34RV4","created_at":"2026-07-05T03:13:36.169581+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBRLZJJ34RV47EYI","created_at":"2026-07-05T03:13:36.169581+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBRLZJJ3","created_at":"2026-07-05T03:13:36.169581+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22644","citing_title":"Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics","ref_index":139,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SBRLZJJ34RV47EYI3EL37MPMNW","json":"https://pith.science/pith/SBRLZJJ34RV47EYI3EL37MPMNW.json","graph_json":"https://pith.science/api/pith-number/SBRLZJJ34RV47EYI3EL37MPMNW/graph.json","events_json":"https://pith.science/api/pith-number/SBRLZJJ34RV47EYI3EL37MPMNW/events.json","paper":"https://pith.science/paper/SBRLZJJ3"},"agent_actions":{"view_html":"https://pith.science/pith/SBRLZJJ34RV47EYI3EL37MPMNW","download_json":"https://pith.science/pith/SBRLZJJ34RV47EYI3EL37MPMNW.json","view_paper":"https://pith.science/paper/SBRLZJJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.05198&json=true","fetch_graph":"https://pith.science/api/pith-number/SBRLZJJ34RV47EYI3EL37MPMNW/graph.json","fetch_events":"https://pith.science/api/pith-number/SBRLZJJ34RV47EYI3EL37MPMNW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBRLZJJ34RV47EYI3EL37MPMNW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBRLZJJ34RV47EYI3EL37MPMNW/action/storage_attestation","attest_author":"https://pith.science/pith/SBRLZJJ34RV47EYI3EL37MPMNW/action/author_attestation","sign_citation":"https://pith.science/pith/SBRLZJJ34RV47EYI3EL37MPMNW/action/citation_signature","submit_replication":"https://pith.science/pith/SBRLZJJ34RV47EYI3EL37MPMNW/action/replication_record"}},"created_at":"2026-07-05T03:13:36.169581+00:00","updated_at":"2026-07-05T03:13:36.169581+00:00"}