{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YQARC22ON5OU2E2EXF6BH7AXN4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"af6748e858da6885d47db2539b925cd00e1f58dacd4095aab6aeb6f4ce733c8b","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-01-31T18:17:25Z","title_canon_sha256":"7ced9cc070a93a289432ed4dfbf40b1537d1910cf913e848146fabeccc63fb4d"},"schema_version":"1.0","source":{"id":"2201.13409","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.13409","created_at":"2026-07-05T09:42:17Z"},{"alias_kind":"arxiv_version","alias_value":"2201.13409v4","created_at":"2026-07-05T09:42:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.13409","created_at":"2026-07-05T09:42:17Z"},{"alias_kind":"pith_short_12","alias_value":"YQARC22ON5OU","created_at":"2026-07-05T09:42:17Z"},{"alias_kind":"pith_short_16","alias_value":"YQARC22ON5OU2E2E","created_at":"2026-07-05T09:42:17Z"},{"alias_kind":"pith_short_8","alias_value":"YQARC22O","created_at":"2026-07-05T09:42:17Z"}],"graph_snapshots":[{"event_id":"sha256:2e2f8030bb02292cff0ccec63905f292f7255db13daf91472b7e861e3ff2d190","target":"graph","created_at":"2026-07-05T09:42:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2201.13409/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bilevel optimization, the problem of minimizing a value function which involves the arg-minimum of another function, appears in many areas of machine learning. In a large scale empirical risk minimization setting where the number of samples is huge, it is crucial to develop stochastic methods, which only use a few samples at a time to progress. However, computing the gradient of the value function involves solving a linear system, which makes it difficult to derive unbiased stochastic estimates. To overcome this problem we introduce a novel framework, in which the solution of the inner problem","authors_text":"Mathieu Dagr\\'eou, Pierre Ablin, Samuel Vaiter, Thomas Moreau","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-01-31T18:17:25Z","title":"A framework for bilevel optimization that enables stochastic and global variance reduction algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.13409","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:09fecd6395248ee48cd61e752dbfe7a2d0177258f244adffa63741af144661e6","target":"record","created_at":"2026-07-05T09:42:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"af6748e858da6885d47db2539b925cd00e1f58dacd4095aab6aeb6f4ce733c8b","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-01-31T18:17:25Z","title_canon_sha256":"7ced9cc070a93a289432ed4dfbf40b1537d1910cf913e848146fabeccc63fb4d"},"schema_version":"1.0","source":{"id":"2201.13409","kind":"arxiv","version":4}},"canonical_sha256":"c401116b4e6f5d4d1344b97c13fc176f2d3d8acf4db7b80fc54ddea7759fb6d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c401116b4e6f5d4d1344b97c13fc176f2d3d8acf4db7b80fc54ddea7759fb6d8","first_computed_at":"2026-07-05T09:42:17.092241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:17.092241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"os3mto9SfhqsYlnIOISYFemOMLkQe7uQWiZELCHFYiQ0sYL0TVVwHo7L6+C450Bqm/Q1B7EP1AhWxhGmKIYHAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:17.092993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.13409","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09fecd6395248ee48cd61e752dbfe7a2d0177258f244adffa63741af144661e6","sha256:2e2f8030bb02292cff0ccec63905f292f7255db13daf91472b7e861e3ff2d190"],"state_sha256":"793524e1a3a84b4fe3e7cb68627cdea3f0dc521687766833fb8f4072df48a5ee"}