{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SOY7X4OMLWYJAQGWBDPIDMBPBC","short_pith_number":"pith:SOY7X4OM","schema_version":"1.0","canonical_sha256":"93b1fbf1cc5db09040d608de81b02f08ae678d9e92bbca9e8650d9678c3bca12","source":{"kind":"arxiv","id":"1908.10525","version":2},"attestation_state":"computed","paper":{"title":"Linear Convergence of Adaptive Stochastic Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Rachel Ward, Xiaoxia Wu, Yuege Xie","submitted_at":"2019-08-28T02:42:50Z","abstract_excerpt":"We prove that the norm version of the adaptive stochastic gradient method (AdaGrad-Norm) achieves a linear convergence rate for a subset of either strongly convex functions or non-convex functions that satisfy the Polyak Lojasiewicz (PL) inequality. The paper introduces the notion of Restricted Uniform Inequality of Gradients (RUIG)---which is a measure of the balanced-ness of the stochastic gradient norms---to depict the landscape of a function. RUIG plays a key role in proving the robustness of AdaGrad-Norm to its hyper-parameter tuning in the stochastic setting. On top of RUIG, we develop 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":"1908.10525","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-28T02:42:50Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"4505c8f68d29207b995a752b272a3c40bcfcbc928b306cf79673c9a43f7c01a4","abstract_canon_sha256":"6657248f172b8b8f37b44febadb45cb97b3024e13afed207c86d2b999a2b1527"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:41.351113Z","signature_b64":"OB56EnlB6Gdl/eqza1deFulgY8rV4ZyP2L0QkwdGTy1TiaQ81pXhFFkacOEQDfZeWXs1kb3TZGW2yRmtxQpWBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93b1fbf1cc5db09040d608de81b02f08ae678d9e92bbca9e8650d9678c3bca12","last_reissued_at":"2026-07-05T01:11:41.350571Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:41.350571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Linear Convergence of Adaptive Stochastic Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Rachel Ward, Xiaoxia Wu, Yuege Xie","submitted_at":"2019-08-28T02:42:50Z","abstract_excerpt":"We prove that the norm version of the adaptive stochastic gradient method (AdaGrad-Norm) achieves a linear convergence rate for a subset of either strongly convex functions or non-convex functions that satisfy the Polyak Lojasiewicz (PL) inequality. The paper introduces the notion of Restricted Uniform Inequality of Gradients (RUIG)---which is a measure of the balanced-ness of the stochastic gradient norms---to depict the landscape of a function. RUIG plays a key role in proving the robustness of AdaGrad-Norm to its hyper-parameter tuning in the stochastic setting. On top of RUIG, we develop a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.10525","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/1908.10525/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":"1908.10525","created_at":"2026-07-05T01:11:41.350630+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.10525v2","created_at":"2026-07-05T01:11:41.350630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10525","created_at":"2026-07-05T01:11:41.350630+00:00"},{"alias_kind":"pith_short_12","alias_value":"SOY7X4OMLWYJ","created_at":"2026-07-05T01:11:41.350630+00:00"},{"alias_kind":"pith_short_16","alias_value":"SOY7X4OMLWYJAQGW","created_at":"2026-07-05T01:11:41.350630+00:00"},{"alias_kind":"pith_short_8","alias_value":"SOY7X4OM","created_at":"2026-07-05T01:11:41.350630+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/SOY7X4OMLWYJAQGWBDPIDMBPBC","json":"https://pith.science/pith/SOY7X4OMLWYJAQGWBDPIDMBPBC.json","graph_json":"https://pith.science/api/pith-number/SOY7X4OMLWYJAQGWBDPIDMBPBC/graph.json","events_json":"https://pith.science/api/pith-number/SOY7X4OMLWYJAQGWBDPIDMBPBC/events.json","paper":"https://pith.science/paper/SOY7X4OM"},"agent_actions":{"view_html":"https://pith.science/pith/SOY7X4OMLWYJAQGWBDPIDMBPBC","download_json":"https://pith.science/pith/SOY7X4OMLWYJAQGWBDPIDMBPBC.json","view_paper":"https://pith.science/paper/SOY7X4OM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.10525&json=true","fetch_graph":"https://pith.science/api/pith-number/SOY7X4OMLWYJAQGWBDPIDMBPBC/graph.json","fetch_events":"https://pith.science/api/pith-number/SOY7X4OMLWYJAQGWBDPIDMBPBC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SOY7X4OMLWYJAQGWBDPIDMBPBC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SOY7X4OMLWYJAQGWBDPIDMBPBC/action/storage_attestation","attest_author":"https://pith.science/pith/SOY7X4OMLWYJAQGWBDPIDMBPBC/action/author_attestation","sign_citation":"https://pith.science/pith/SOY7X4OMLWYJAQGWBDPIDMBPBC/action/citation_signature","submit_replication":"https://pith.science/pith/SOY7X4OMLWYJAQGWBDPIDMBPBC/action/replication_record"}},"created_at":"2026-07-05T01:11:41.350630+00:00","updated_at":"2026-07-05T01:11:41.350630+00:00"}