{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NYXJYHXJXA3AXM2VT5RFE4Y42N","short_pith_number":"pith:NYXJYHXJ","schema_version":"1.0","canonical_sha256":"6e2e9c1ee9b8360bb3559f6252731cd35a47c8dbba7e416821a5189bb4828714","source":{"kind":"arxiv","id":"2002.05359","version":1},"attestation_state":"computed","paper":{"title":"Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lihua Lei, Michael I. Jordan, Peter Richt\\'arik, Samuel Horv\\'ath","submitted_at":"2020-02-13T05:42:27Z","abstract_excerpt":"Adaptivity is an important yet under-studied property in modern optimization theory. The gap between the state-of-the-art theory and the current practice is striking in that algorithms with desirable theoretical guarantees typically involve drastically different settings of hyperparameters, such as step-size schemes and batch sizes, in different regimes. Despite the appealing theoretical results, such divisive strategies provide little, if any, insight to practitioners to select algorithms that work broadly without tweaking the hyperparameters. In this work, blending the \"geometrization\" techn"},"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":"2002.05359","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-13T05:42:27Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"00de360eac13171cc6fe0caf9a023dc116724fb9a634316b45c7acc12dba9a1a","abstract_canon_sha256":"59bc45adf4aa2e566ca09432bb313547ca5249112ee97cda44ad9317b17d64d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:30.564222Z","signature_b64":"BQE3l62LnCC00JyRVxu/rg4wVPvivU54MsiatLHzweC984Jc1f/5JYOSyglOOdkIIuM2ZhWp0sLvAyzrdY/IBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e2e9c1ee9b8360bb3559f6252731cd35a47c8dbba7e416821a5189bb4828714","last_reissued_at":"2026-07-05T00:40:30.563776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:30.563776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lihua Lei, Michael I. Jordan, Peter Richt\\'arik, Samuel Horv\\'ath","submitted_at":"2020-02-13T05:42:27Z","abstract_excerpt":"Adaptivity is an important yet under-studied property in modern optimization theory. The gap between the state-of-the-art theory and the current practice is striking in that algorithms with desirable theoretical guarantees typically involve drastically different settings of hyperparameters, such as step-size schemes and batch sizes, in different regimes. Despite the appealing theoretical results, such divisive strategies provide little, if any, insight to practitioners to select algorithms that work broadly without tweaking the hyperparameters. In this work, blending the \"geometrization\" techn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05359","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/2002.05359/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":"2002.05359","created_at":"2026-07-05T00:40:30.563842+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.05359v1","created_at":"2026-07-05T00:40:30.563842+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05359","created_at":"2026-07-05T00:40:30.563842+00:00"},{"alias_kind":"pith_short_12","alias_value":"NYXJYHXJXA3A","created_at":"2026-07-05T00:40:30.563842+00:00"},{"alias_kind":"pith_short_16","alias_value":"NYXJYHXJXA3AXM2V","created_at":"2026-07-05T00:40:30.563842+00:00"},{"alias_kind":"pith_short_8","alias_value":"NYXJYHXJ","created_at":"2026-07-05T00:40:30.563842+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/NYXJYHXJXA3AXM2VT5RFE4Y42N","json":"https://pith.science/pith/NYXJYHXJXA3AXM2VT5RFE4Y42N.json","graph_json":"https://pith.science/api/pith-number/NYXJYHXJXA3AXM2VT5RFE4Y42N/graph.json","events_json":"https://pith.science/api/pith-number/NYXJYHXJXA3AXM2VT5RFE4Y42N/events.json","paper":"https://pith.science/paper/NYXJYHXJ"},"agent_actions":{"view_html":"https://pith.science/pith/NYXJYHXJXA3AXM2VT5RFE4Y42N","download_json":"https://pith.science/pith/NYXJYHXJXA3AXM2VT5RFE4Y42N.json","view_paper":"https://pith.science/paper/NYXJYHXJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.05359&json=true","fetch_graph":"https://pith.science/api/pith-number/NYXJYHXJXA3AXM2VT5RFE4Y42N/graph.json","fetch_events":"https://pith.science/api/pith-number/NYXJYHXJXA3AXM2VT5RFE4Y42N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NYXJYHXJXA3AXM2VT5RFE4Y42N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NYXJYHXJXA3AXM2VT5RFE4Y42N/action/storage_attestation","attest_author":"https://pith.science/pith/NYXJYHXJXA3AXM2VT5RFE4Y42N/action/author_attestation","sign_citation":"https://pith.science/pith/NYXJYHXJXA3AXM2VT5RFE4Y42N/action/citation_signature","submit_replication":"https://pith.science/pith/NYXJYHXJXA3AXM2VT5RFE4Y42N/action/replication_record"}},"created_at":"2026-07-05T00:40:30.563842+00:00","updated_at":"2026-07-05T00:40:30.563842+00:00"}