{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RFMF3DGLEFEN5B4HWO4E45S3FO","short_pith_number":"pith:RFMF3DGL","schema_version":"1.0","canonical_sha256":"89585d8ccb2148de8787b3b84e765b2b860e641c8543e406435dee5dc3cb59dc","source":{"kind":"arxiv","id":"2509.15543","version":2},"attestation_state":"computed","paper":{"title":"Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Heng Liang, Hongchang Gao, Xinwen Zhang, Yihan Zhang","submitted_at":"2025-09-19T02:51:19Z","abstract_excerpt":"Existing decentralized stochastic optimization methods assume the lower-level loss function is strongly convex and the stochastic gradient noise has finite variance. These strong assumptions typically are not satisfied in real-world machine learning models. For example, learning on language data typically leads to heavy-tailed gradient. To address these limitations, we develop a novel decentralized stochastic bilevel optimization algorithm for the nonconvex bilevel optimization problem under heavy-tailed noise. Specifically, we develop a normalized stochastic variance-reduced bilevel gradient "},"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":"2509.15543","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-19T02:51:19Z","cross_cats_sorted":[],"title_canon_sha256":"26650d4bccc1ae52f14bd387616a2b03ff8e2cb9576d558f90c14a3820f7fdc6","abstract_canon_sha256":"907531696645a81c6c6c5a85e40f36c274d897166abad88ece626d35a8f40653"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:02.139470Z","signature_b64":"Y75qkyIafRx3KynqvlW8lUp1T/MIsPnGQ6UlgZiG+8ulQgCnl9PdPS/MEvUrbvs26ZpM+dZBLcrMVsLrlkoDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89585d8ccb2148de8787b3b84e765b2b860e641c8543e406435dee5dc3cb59dc","last_reissued_at":"2026-05-26T02:05:02.138663Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:02.138663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Heng Liang, Hongchang Gao, Xinwen Zhang, Yihan Zhang","submitted_at":"2025-09-19T02:51:19Z","abstract_excerpt":"Existing decentralized stochastic optimization methods assume the lower-level loss function is strongly convex and the stochastic gradient noise has finite variance. These strong assumptions typically are not satisfied in real-world machine learning models. For example, learning on language data typically leads to heavy-tailed gradient. To address these limitations, we develop a novel decentralized stochastic bilevel optimization algorithm for the nonconvex bilevel optimization problem under heavy-tailed noise. Specifically, we develop a normalized stochastic variance-reduced bilevel gradient "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.15543","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/2509.15543/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":"2509.15543","created_at":"2026-05-26T02:05:02.138774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.15543v2","created_at":"2026-05-26T02:05:02.138774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.15543","created_at":"2026-05-26T02:05:02.138774+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFMF3DGLEFEN","created_at":"2026-05-26T02:05:02.138774+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFMF3DGLEFEN5B4H","created_at":"2026-05-26T02:05:02.138774+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFMF3DGL","created_at":"2026-05-26T02:05:02.138774+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/RFMF3DGLEFEN5B4HWO4E45S3FO","json":"https://pith.science/pith/RFMF3DGLEFEN5B4HWO4E45S3FO.json","graph_json":"https://pith.science/api/pith-number/RFMF3DGLEFEN5B4HWO4E45S3FO/graph.json","events_json":"https://pith.science/api/pith-number/RFMF3DGLEFEN5B4HWO4E45S3FO/events.json","paper":"https://pith.science/paper/RFMF3DGL"},"agent_actions":{"view_html":"https://pith.science/pith/RFMF3DGLEFEN5B4HWO4E45S3FO","download_json":"https://pith.science/pith/RFMF3DGLEFEN5B4HWO4E45S3FO.json","view_paper":"https://pith.science/paper/RFMF3DGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.15543&json=true","fetch_graph":"https://pith.science/api/pith-number/RFMF3DGLEFEN5B4HWO4E45S3FO/graph.json","fetch_events":"https://pith.science/api/pith-number/RFMF3DGLEFEN5B4HWO4E45S3FO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFMF3DGLEFEN5B4HWO4E45S3FO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFMF3DGLEFEN5B4HWO4E45S3FO/action/storage_attestation","attest_author":"https://pith.science/pith/RFMF3DGLEFEN5B4HWO4E45S3FO/action/author_attestation","sign_citation":"https://pith.science/pith/RFMF3DGLEFEN5B4HWO4E45S3FO/action/citation_signature","submit_replication":"https://pith.science/pith/RFMF3DGLEFEN5B4HWO4E45S3FO/action/replication_record"}},"created_at":"2026-05-26T02:05:02.138774+00:00","updated_at":"2026-05-26T02:05:02.138774+00:00"}