{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:U5YWIRUBK53YWYDI67FK4ZNCL4","short_pith_number":"pith:U5YWIRUB","schema_version":"1.0","canonical_sha256":"a77164468157778b6068f7caae65a25f24f23d836a62c90700f49814357bb30c","source":{"kind":"arxiv","id":"1706.06569","version":1},"attestation_state":"computed","paper":{"title":"A Unified Approach to Adaptive Regularization in Online and Stochastic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tomer Koren, Vineet Gupta, Yoram Singer","submitted_at":"2017-06-20T17:51:00Z","abstract_excerpt":"We describe a framework for deriving and analyzing online optimization algorithms that incorporate adaptive, data-dependent regularization, also termed preconditioning. Such algorithms have been proven useful in stochastic optimization by reshaping the gradients according to the geometry of the data. Our framework captures and unifies much of the existing literature on adaptive online methods, including the AdaGrad and Online Newton Step algorithms as well as their diagonal versions. As a result, we obtain new convergence proofs for these algorithms that are substantially simpler than previous"},"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":"1706.06569","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-20T17:51:00Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"50dd9cdfb00a87f2b03006b1897eecc0360e120f7feb9af1cb95440026733393","abstract_canon_sha256":"29f21279e25c99f4ba0cc0aad1893b8274a4f0655f1d1bb00cb43787ace23a6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:02.896020Z","signature_b64":"0RQVtbTKeNKvGQXUCA+uawtuc6/pBRFqZtgbHP+C5eWBn13TAvF7qzB2bMpY+CJP6vaimQNux3w1PFcIxMAaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a77164468157778b6068f7caae65a25f24f23d836a62c90700f49814357bb30c","last_reissued_at":"2026-05-18T00:42:02.895392Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:02.895392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Approach to Adaptive Regularization in Online and Stochastic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tomer Koren, Vineet Gupta, Yoram Singer","submitted_at":"2017-06-20T17:51:00Z","abstract_excerpt":"We describe a framework for deriving and analyzing online optimization algorithms that incorporate adaptive, data-dependent regularization, also termed preconditioning. Such algorithms have been proven useful in stochastic optimization by reshaping the gradients according to the geometry of the data. Our framework captures and unifies much of the existing literature on adaptive online methods, including the AdaGrad and Online Newton Step algorithms as well as their diagonal versions. As a result, we obtain new convergence proofs for these algorithms that are substantially simpler than previous"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.06569","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":""},"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":"1706.06569","created_at":"2026-05-18T00:42:02.895515+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.06569v1","created_at":"2026-05-18T00:42:02.895515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.06569","created_at":"2026-05-18T00:42:02.895515+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5YWIRUBK53Y","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5YWIRUBK53YWYDI","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5YWIRUB","created_at":"2026-05-18T12:31:46.661854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.07529","citing_title":"Training Deep Learning Models with Norm-Constrained LMOs","ref_index":179,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08980","citing_title":"Muon Does Not Converge on Convex Lipschitz Functions","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10728","citing_title":"Last Iterate Convergence of AdaGrad-Norm for Convex Non-Smooth Optimization","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06525","citing_title":"Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17423","citing_title":"A unified convergence theory for adaptive first-order methods in the nonconvex case, including AdaNorm, full and diagonal AdaGrad, Shampoo and Muo","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5YWIRUBK53YWYDI67FK4ZNCL4","json":"https://pith.science/pith/U5YWIRUBK53YWYDI67FK4ZNCL4.json","graph_json":"https://pith.science/api/pith-number/U5YWIRUBK53YWYDI67FK4ZNCL4/graph.json","events_json":"https://pith.science/api/pith-number/U5YWIRUBK53YWYDI67FK4ZNCL4/events.json","paper":"https://pith.science/paper/U5YWIRUB"},"agent_actions":{"view_html":"https://pith.science/pith/U5YWIRUBK53YWYDI67FK4ZNCL4","download_json":"https://pith.science/pith/U5YWIRUBK53YWYDI67FK4ZNCL4.json","view_paper":"https://pith.science/paper/U5YWIRUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.06569&json=true","fetch_graph":"https://pith.science/api/pith-number/U5YWIRUBK53YWYDI67FK4ZNCL4/graph.json","fetch_events":"https://pith.science/api/pith-number/U5YWIRUBK53YWYDI67FK4ZNCL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5YWIRUBK53YWYDI67FK4ZNCL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5YWIRUBK53YWYDI67FK4ZNCL4/action/storage_attestation","attest_author":"https://pith.science/pith/U5YWIRUBK53YWYDI67FK4ZNCL4/action/author_attestation","sign_citation":"https://pith.science/pith/U5YWIRUBK53YWYDI67FK4ZNCL4/action/citation_signature","submit_replication":"https://pith.science/pith/U5YWIRUBK53YWYDI67FK4ZNCL4/action/replication_record"}},"created_at":"2026-05-18T00:42:02.895515+00:00","updated_at":"2026-05-18T00:42:02.895515+00:00"}