{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ABYR6WZO5RJ5RROGRAZIAIJ6DT","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":"666efc8ecc3a129cd3a73f2006db274f9d5c427db23754c4c0c7732c6fdaeadb","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-17T16:37:08Z","title_canon_sha256":"8a5cc08967c38aaae2efc01ff045a3a65fa9771dd6cd5057f3a437d8a40fc5e9"},"schema_version":"1.0","source":{"id":"2302.08982","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.08982","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2302.08982v2","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08982","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"ABYR6WZO5RJ5","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"ABYR6WZO5RJ5RROG","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"ABYR6WZO","created_at":"2026-07-05T07:04:45Z"}],"graph_snapshots":[{"event_id":"sha256:bacfb3f0fa7294690955dcc582ae4a56ae4303b437feb1967665ee1999cdb71a","target":"graph","created_at":"2026-07-05T07:04:45Z","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/2302.08982/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we investigate the impact of stochasticity and large stepsizes on the implicit regularisation of gradient descent (GD) and stochastic gradient descent (SGD) over diagonal linear networks. We prove the convergence of GD and SGD with macroscopic stepsizes in an overparametrised regression setting and characterise their solutions through an implicit regularisation problem. Our crisp characterisation leads to qualitative insights about the impact of stochasticity and stepsizes on the recovered solution. Specifically, we show that large stepsizes consistently benefit SGD for sparse r","authors_text":"Mathieu Even, Nicolas Flammarion, Scott Pesme, Suriya Gunasekar","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-17T16:37:08Z","title":"(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08982","kind":"arxiv","version":2},"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":"sha256:98ff1cdd349df43f8e73ba97db557e2a44f5feba8c7913df5a42409d2f84f091","target":"record","created_at":"2026-07-05T07:04:45Z","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":"666efc8ecc3a129cd3a73f2006db274f9d5c427db23754c4c0c7732c6fdaeadb","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-17T16:37:08Z","title_canon_sha256":"8a5cc08967c38aaae2efc01ff045a3a65fa9771dd6cd5057f3a437d8a40fc5e9"},"schema_version":"1.0","source":{"id":"2302.08982","kind":"arxiv","version":2}},"canonical_sha256":"00711f5b2eec53d8c5c6883280213e1cd29f56d1bdd1bbfc9abb2f7fd2b25f0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00711f5b2eec53d8c5c6883280213e1cd29f56d1bdd1bbfc9abb2f7fd2b25f0b","first_computed_at":"2026-07-05T07:04:45.327810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:45.327810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mc0qMWFAIeRtrScFxD6rVMSdRYWqgIHdBX6tIRJgL0BCLdfqFG1CL1tw9jyXvS6ItjQ4kH/5sgWyRf/Gx/1TDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:45.328208Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.08982","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98ff1cdd349df43f8e73ba97db557e2a44f5feba8c7913df5a42409d2f84f091","sha256:bacfb3f0fa7294690955dcc582ae4a56ae4303b437feb1967665ee1999cdb71a"],"state_sha256":"027d5c2e5cda7cef899c79b023982121ba5177f626085d913b6b3165a9aa4fae"}