{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YJBKOT33SAPL22WE4ZIVW2MUWA","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":"ef1dc3a52faa45d0cfae2d948ea9ad317b90e63369a607e62d6d0f83f25d6b47","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-25T09:40:10Z","title_canon_sha256":"8449ea9f2249b6eefcee4bd2b37c67cf7a685cf89834933c9925d6f1657431eb"},"schema_version":"1.0","source":{"id":"2504.18208","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.18208","created_at":"2026-07-05T11:40:34Z"},{"alias_kind":"arxiv_version","alias_value":"2504.18208v2","created_at":"2026-07-05T11:40:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18208","created_at":"2026-07-05T11:40:34Z"},{"alias_kind":"pith_short_12","alias_value":"YJBKOT33SAPL","created_at":"2026-07-05T11:40:34Z"},{"alias_kind":"pith_short_16","alias_value":"YJBKOT33SAPL22WE","created_at":"2026-07-05T11:40:34Z"},{"alias_kind":"pith_short_8","alias_value":"YJBKOT33","created_at":"2026-07-05T11:40:34Z"}],"graph_snapshots":[{"event_id":"sha256:93ceaaeed618b17e4d62aa42787c7251b4cb548cd96a722f9a4f21ff9c7cb1f4","target":"graph","created_at":"2026-07-05T11:40:34Z","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/2504.18208/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the convergence of gradient methods for the training of mean-field single-hidden-layer neural networks with square loss. For this high-dimensional and non-convex optimization problem, most known convergence results are either qualitative or rely on a neural tangent kernel analysis where nonlinear representations of the data are fixed. Using that this problem belongs to the class of separable nonlinear least squares problems, we consider here a Variable Projection (VarPro) or two-timescale learning algorithm, thereby eliminating the linear variables and reducing the learning problem to","authors_text":"\\'ENS-PSL), Fran\\c{c}ois-Xavier Vialard (LIGM), Gabriel Peyr\\'e (CNRS, Rapha\\\"el Barboni (\\'ENS-PSL)","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-25T09:40:10Z","title":"Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18208","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":"sha256:8c114c22c5133766f48bd6946b1fc3cebe38ae0c375addc6988ebf216ef6c642","target":"record","created_at":"2026-07-05T11:40:34Z","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":"ef1dc3a52faa45d0cfae2d948ea9ad317b90e63369a607e62d6d0f83f25d6b47","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-25T09:40:10Z","title_canon_sha256":"8449ea9f2249b6eefcee4bd2b37c67cf7a685cf89834933c9925d6f1657431eb"},"schema_version":"1.0","source":{"id":"2504.18208","kind":"arxiv","version":2}},"canonical_sha256":"c242a74f7b901ebd6ac4e6515b6994b02dac4eb005ff915992d055a49b92db22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c242a74f7b901ebd6ac4e6515b6994b02dac4eb005ff915992d055a49b92db22","first_computed_at":"2026-07-05T11:40:34.065961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:34.065961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J2AxVaro0G3NMp2olApklTRx6rSnSLW7YK7bcjThIzjxGcsOjzRcj74/9RIYhhfIpfKYaVcttTgE3crR5gNtDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:34.066384Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.18208","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c114c22c5133766f48bd6946b1fc3cebe38ae0c375addc6988ebf216ef6c642","sha256:93ceaaeed618b17e4d62aa42787c7251b4cb548cd96a722f9a4f21ff9c7cb1f4"],"state_sha256":"1f8e5d10d17f21ec8c82eb0a01786ca723007457ad2cc4951d5654c75f9449c6"}