{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WXJZNZCKHE5IMQZM34GAX57UN3","short_pith_number":"pith:WXJZNZCK","schema_version":"1.0","canonical_sha256":"b5d396e44a393a86432cdf0c0bf7f46ec6ff857b655db8c1d3202a153b03e95e","source":{"kind":"arxiv","id":"2307.06987","version":1},"attestation_state":"computed","paper":{"title":"A new non-convex framework to improve asymptotical knowledge on generic stochastic gradient descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Audrey Repetti, Emilie Chouzenoux, Jean-Baptiste Fest","submitted_at":"2023-07-13T17:49:49Z","abstract_excerpt":"Stochastic gradient optimization methods are broadly used to minimize non-convex smooth objective functions, for instance when training deep neural networks. However, theoretical guarantees on the asymptotic behaviour of these methods remain scarce. Especially, ensuring almost-sure convergence of the iterates to a stationary point is quite challenging. In this work, we introduce a new Kurdyka-Lojasiewicz theoretical framework to analyze asymptotic behavior of stochastic gradient descent (SGD) schemes when minimizing non-convex smooth objectives. In particular, our framework provides new almost"},"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":"2307.06987","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-07-13T17:49:49Z","cross_cats_sorted":[],"title_canon_sha256":"cd4a134b7d14913b1c6b50dc12f599290ee6b5e0d076334558f55a510a447177","abstract_canon_sha256":"90ad9164029f7b00e2326d747adc621e373772f209b996df5c870216dfe9ebf2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:48.710965Z","signature_b64":"oMziIz/m9/8Ms+nUwpjDWZR5PWQGj5Le168zlIU4UV61oLQSplS07xQMYhrZmgv9XYFQWplNlj01gmTGygfRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5d396e44a393a86432cdf0c0bf7f46ec6ff857b655db8c1d3202a153b03e95e","last_reissued_at":"2026-07-05T06:30:48.710436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:48.710436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A new non-convex framework to improve asymptotical knowledge on generic stochastic gradient descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Audrey Repetti, Emilie Chouzenoux, Jean-Baptiste Fest","submitted_at":"2023-07-13T17:49:49Z","abstract_excerpt":"Stochastic gradient optimization methods are broadly used to minimize non-convex smooth objective functions, for instance when training deep neural networks. However, theoretical guarantees on the asymptotic behaviour of these methods remain scarce. Especially, ensuring almost-sure convergence of the iterates to a stationary point is quite challenging. In this work, we introduce a new Kurdyka-Lojasiewicz theoretical framework to analyze asymptotic behavior of stochastic gradient descent (SGD) schemes when minimizing non-convex smooth objectives. In particular, our framework provides new almost"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06987","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/2307.06987/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":"2307.06987","created_at":"2026-07-05T06:30:48.710510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.06987v1","created_at":"2026-07-05T06:30:48.710510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06987","created_at":"2026-07-05T06:30:48.710510+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXJZNZCKHE5I","created_at":"2026-07-05T06:30:48.710510+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXJZNZCKHE5IMQZM","created_at":"2026-07-05T06:30:48.710510+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXJZNZCK","created_at":"2026-07-05T06:30:48.710510+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/WXJZNZCKHE5IMQZM34GAX57UN3","json":"https://pith.science/pith/WXJZNZCKHE5IMQZM34GAX57UN3.json","graph_json":"https://pith.science/api/pith-number/WXJZNZCKHE5IMQZM34GAX57UN3/graph.json","events_json":"https://pith.science/api/pith-number/WXJZNZCKHE5IMQZM34GAX57UN3/events.json","paper":"https://pith.science/paper/WXJZNZCK"},"agent_actions":{"view_html":"https://pith.science/pith/WXJZNZCKHE5IMQZM34GAX57UN3","download_json":"https://pith.science/pith/WXJZNZCKHE5IMQZM34GAX57UN3.json","view_paper":"https://pith.science/paper/WXJZNZCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.06987&json=true","fetch_graph":"https://pith.science/api/pith-number/WXJZNZCKHE5IMQZM34GAX57UN3/graph.json","fetch_events":"https://pith.science/api/pith-number/WXJZNZCKHE5IMQZM34GAX57UN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXJZNZCKHE5IMQZM34GAX57UN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXJZNZCKHE5IMQZM34GAX57UN3/action/storage_attestation","attest_author":"https://pith.science/pith/WXJZNZCKHE5IMQZM34GAX57UN3/action/author_attestation","sign_citation":"https://pith.science/pith/WXJZNZCKHE5IMQZM34GAX57UN3/action/citation_signature","submit_replication":"https://pith.science/pith/WXJZNZCKHE5IMQZM34GAX57UN3/action/replication_record"}},"created_at":"2026-07-05T06:30:48.710510+00:00","updated_at":"2026-07-05T06:30:48.710510+00:00"}