{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:34TL7WT24BTS7UZN7NLX7JITQY","short_pith_number":"pith:34TL7WT2","schema_version":"1.0","canonical_sha256":"df26bfda7ae0672fd32dfb577fa513862a59a885380c7de7d0e2763f5e98f689","source":{"kind":"arxiv","id":"2306.08109","version":2},"attestation_state":"computed","paper":{"title":"Provable Accelerated Convergence of Nesterov's Momentum for Deep ReLU Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Anastasios Kyrillidis, Fangshuo Liao","submitted_at":"2023-06-13T19:55:46Z","abstract_excerpt":"Current state-of-the-art analyses on the convergence of gradient descent for training neural networks focus on characterizing properties of the loss landscape, such as the Polyak-Lojaciewicz (PL) condition and the restricted strong convexity. While gradient descent converges linearly under such conditions, it remains an open question whether Nesterov's momentum enjoys accelerated convergence under similar settings and assumptions. In this work, we consider a new class of objective functions, where only a subset of the parameters satisfies strong convexity, and show Nesterov's momentum achieves"},"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":"2306.08109","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T19:55:46Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"8ba37eda27da718263c32a99148afa768bf86a2483a475fd6290313f006f4b66","abstract_canon_sha256":"37d8bebd44e2acd60eb0cd68535791b4941f35948a8fbac7c9729dcc9b818500"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:19.820227Z","signature_b64":"H+jWBqC0lnQARKSCixR+Y0oRhN/zahXxTq2ix7qOLcagl8AHXK4xGpvJrovo/SmDvfUp5K5UiAC/ilRWuW2zCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df26bfda7ae0672fd32dfb577fa513862a59a885380c7de7d0e2763f5e98f689","last_reissued_at":"2026-07-05T07:30:19.819824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:19.819824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provable Accelerated Convergence of Nesterov's Momentum for Deep ReLU Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Anastasios Kyrillidis, Fangshuo Liao","submitted_at":"2023-06-13T19:55:46Z","abstract_excerpt":"Current state-of-the-art analyses on the convergence of gradient descent for training neural networks focus on characterizing properties of the loss landscape, such as the Polyak-Lojaciewicz (PL) condition and the restricted strong convexity. While gradient descent converges linearly under such conditions, it remains an open question whether Nesterov's momentum enjoys accelerated convergence under similar settings and assumptions. In this work, we consider a new class of objective functions, where only a subset of the parameters satisfies strong convexity, and show Nesterov's momentum achieves"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08109","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/2306.08109/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":"2306.08109","created_at":"2026-07-05T07:30:19.819880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.08109v2","created_at":"2026-07-05T07:30:19.819880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08109","created_at":"2026-07-05T07:30:19.819880+00:00"},{"alias_kind":"pith_short_12","alias_value":"34TL7WT24BTS","created_at":"2026-07-05T07:30:19.819880+00:00"},{"alias_kind":"pith_short_16","alias_value":"34TL7WT24BTS7UZN","created_at":"2026-07-05T07:30:19.819880+00:00"},{"alias_kind":"pith_short_8","alias_value":"34TL7WT2","created_at":"2026-07-05T07:30:19.819880+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/34TL7WT24BTS7UZN7NLX7JITQY","json":"https://pith.science/pith/34TL7WT24BTS7UZN7NLX7JITQY.json","graph_json":"https://pith.science/api/pith-number/34TL7WT24BTS7UZN7NLX7JITQY/graph.json","events_json":"https://pith.science/api/pith-number/34TL7WT24BTS7UZN7NLX7JITQY/events.json","paper":"https://pith.science/paper/34TL7WT2"},"agent_actions":{"view_html":"https://pith.science/pith/34TL7WT24BTS7UZN7NLX7JITQY","download_json":"https://pith.science/pith/34TL7WT24BTS7UZN7NLX7JITQY.json","view_paper":"https://pith.science/paper/34TL7WT2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.08109&json=true","fetch_graph":"https://pith.science/api/pith-number/34TL7WT24BTS7UZN7NLX7JITQY/graph.json","fetch_events":"https://pith.science/api/pith-number/34TL7WT24BTS7UZN7NLX7JITQY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/34TL7WT24BTS7UZN7NLX7JITQY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/34TL7WT24BTS7UZN7NLX7JITQY/action/storage_attestation","attest_author":"https://pith.science/pith/34TL7WT24BTS7UZN7NLX7JITQY/action/author_attestation","sign_citation":"https://pith.science/pith/34TL7WT24BTS7UZN7NLX7JITQY/action/citation_signature","submit_replication":"https://pith.science/pith/34TL7WT24BTS7UZN7NLX7JITQY/action/replication_record"}},"created_at":"2026-07-05T07:30:19.819880+00:00","updated_at":"2026-07-05T07:30:19.819880+00:00"}