{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GLI32OL74OYXXBEXPXEKY4SHK3","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":"787b667d612d7d3707e65335e2f204376dd361779eabad1e29ccd94088ee2505","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T19:57:22Z","title_canon_sha256":"339613fa38584a84baff1409057656692bb1aa04766255aba88af76405c0cbe1"},"schema_version":"1.0","source":{"id":"2505.11664","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11664","created_at":"2026-07-05T11:04:25Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11664v1","created_at":"2026-07-05T11:04:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11664","created_at":"2026-07-05T11:04:25Z"},{"alias_kind":"pith_short_12","alias_value":"GLI32OL74OYX","created_at":"2026-07-05T11:04:25Z"},{"alias_kind":"pith_short_16","alias_value":"GLI32OL74OYXXBEX","created_at":"2026-07-05T11:04:25Z"},{"alias_kind":"pith_short_8","alias_value":"GLI32OL7","created_at":"2026-07-05T11:04:25Z"}],"graph_snapshots":[{"event_id":"sha256:e9406ebb28ccdc9d50eeeb4422b4bd13b652348bd4bc02b748fe00b9959f29e2","target":"graph","created_at":"2026-07-05T11:04:25Z","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/2505.11664/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most prior work on the convergence of gradient descent (GD) for overparameterized neural networks relies on strong assumptions on the step size (infinitesimal), the hidden-layer width (infinite), or the initialization (large, spectral, balanced). Recent efforts to relax these assumptions focus on two-layer linear networks trained with the squared loss. In this work, we derive a linear convergence rate for training two-layer linear neural networks with GD for general losses and under relaxed assumptions on the step size, width, and initialization. A key challenge in deriving this result is that","authors_text":"Enrique Mallada, Hancheng Min, Rene Vidal, Salma Tarmoun, Ziqing Xu","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T19:57:22Z","title":"A Local Polyak-Lojasiewicz and Descent Lemma of Gradient Descent For Overparametrized Linear Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11664","kind":"arxiv","version":1},"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":"sha256:09cfdc66f4578192909432199d19fd4dbff20a3de2c72534dea94082d931e166","target":"record","created_at":"2026-07-05T11:04:25Z","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":"787b667d612d7d3707e65335e2f204376dd361779eabad1e29ccd94088ee2505","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T19:57:22Z","title_canon_sha256":"339613fa38584a84baff1409057656692bb1aa04766255aba88af76405c0cbe1"},"schema_version":"1.0","source":{"id":"2505.11664","kind":"arxiv","version":1}},"canonical_sha256":"32d1bd397fe3b17b84977dc8ac724756d54b15925febd40c64f3b22558512266","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32d1bd397fe3b17b84977dc8ac724756d54b15925febd40c64f3b22558512266","first_computed_at":"2026-07-05T11:04:25.086043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:25.086043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XP9BHMCTSbmV/s5Y7CX3NYdrEZZxA1IynDy4MAHaWbi/UMKYKXTUPyz+TvM8jN3U4tK8sY+FbWff83hs7XtEBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:25.086611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11664","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09cfdc66f4578192909432199d19fd4dbff20a3de2c72534dea94082d931e166","sha256:e9406ebb28ccdc9d50eeeb4422b4bd13b652348bd4bc02b748fe00b9959f29e2"],"state_sha256":"a3c67b25cdd25075dffecf1ba94055f3278f524d06beb691abcfeb1cbc6d15d3"}