{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V6LMPOJMKSZRN7GWHEU7IBM246","short_pith_number":"pith:V6LMPOJM","schema_version":"1.0","canonical_sha256":"af96c7b92c54b316fcd63929f4059ae794817235af7382310f0d53c40ab6aeac","source":{"kind":"arxiv","id":"2411.13169","version":1},"attestation_state":"computed","paper":{"title":"A Unified Analysis for Finite Weight Averaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Guodong Zheng, Li Shen, Peng Wang, Yan Sun, Zerui Tao","submitted_at":"2024-11-20T10:08:22Z","abstract_excerpt":"Averaging iterations of Stochastic Gradient Descent (SGD) have achieved empirical success in training deep learning models, such as Stochastic Weight Averaging (SWA), Exponential Moving Average (EMA), and LAtest Weight Averaging (LAWA). Especially, with a finite weight averaging method, LAWA can attain faster convergence and better generalization. However, its theoretical explanation is still less explored since there are fundamental differences between finite and infinite settings. In this work, we first generalize SGD and LAWA as Finite Weight Averaging (FWA) and explain their advantages com"},"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":"2411.13169","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T10:08:22Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"94eced3948a2349320b0e6177dbefa1765c49117fc5c7ece6d4421dbd8ed3236","abstract_canon_sha256":"685973b78943e9003b253d2e44247fb563d935cc7cadb56c0e4bb29489c51332"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:06.231538Z","signature_b64":"iH0EZSPQzQKsjZqbXmbpBCIBNJBUGXT6xMJgnx2hd4l8v8u+li/L5JStobMvCQhpatSDPqATeve2ILyGGiAfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af96c7b92c54b316fcd63929f4059ae794817235af7382310f0d53c40ab6aeac","last_reissued_at":"2026-07-05T09:38:06.231071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:06.231071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Analysis for Finite Weight Averaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Guodong Zheng, Li Shen, Peng Wang, Yan Sun, Zerui Tao","submitted_at":"2024-11-20T10:08:22Z","abstract_excerpt":"Averaging iterations of Stochastic Gradient Descent (SGD) have achieved empirical success in training deep learning models, such as Stochastic Weight Averaging (SWA), Exponential Moving Average (EMA), and LAtest Weight Averaging (LAWA). Especially, with a finite weight averaging method, LAWA can attain faster convergence and better generalization. However, its theoretical explanation is still less explored since there are fundamental differences between finite and infinite settings. In this work, we first generalize SGD and LAWA as Finite Weight Averaging (FWA) and explain their advantages com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13169","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/2411.13169/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":"2411.13169","created_at":"2026-07-05T09:38:06.231138+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13169v1","created_at":"2026-07-05T09:38:06.231138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13169","created_at":"2026-07-05T09:38:06.231138+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6LMPOJMKSZR","created_at":"2026-07-05T09:38:06.231138+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6LMPOJMKSZRN7GW","created_at":"2026-07-05T09:38:06.231138+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6LMPOJM","created_at":"2026-07-05T09:38:06.231138+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/V6LMPOJMKSZRN7GWHEU7IBM246","json":"https://pith.science/pith/V6LMPOJMKSZRN7GWHEU7IBM246.json","graph_json":"https://pith.science/api/pith-number/V6LMPOJMKSZRN7GWHEU7IBM246/graph.json","events_json":"https://pith.science/api/pith-number/V6LMPOJMKSZRN7GWHEU7IBM246/events.json","paper":"https://pith.science/paper/V6LMPOJM"},"agent_actions":{"view_html":"https://pith.science/pith/V6LMPOJMKSZRN7GWHEU7IBM246","download_json":"https://pith.science/pith/V6LMPOJMKSZRN7GWHEU7IBM246.json","view_paper":"https://pith.science/paper/V6LMPOJM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13169&json=true","fetch_graph":"https://pith.science/api/pith-number/V6LMPOJMKSZRN7GWHEU7IBM246/graph.json","fetch_events":"https://pith.science/api/pith-number/V6LMPOJMKSZRN7GWHEU7IBM246/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6LMPOJMKSZRN7GWHEU7IBM246/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6LMPOJMKSZRN7GWHEU7IBM246/action/storage_attestation","attest_author":"https://pith.science/pith/V6LMPOJMKSZRN7GWHEU7IBM246/action/author_attestation","sign_citation":"https://pith.science/pith/V6LMPOJMKSZRN7GWHEU7IBM246/action/citation_signature","submit_replication":"https://pith.science/pith/V6LMPOJMKSZRN7GWHEU7IBM246/action/replication_record"}},"created_at":"2026-07-05T09:38:06.231138+00:00","updated_at":"2026-07-05T09:38:06.231138+00:00"}