{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z67S36JM5FGVXYO3NEUZPJMA4Q","short_pith_number":"pith:Z67S36JM","schema_version":"1.0","canonical_sha256":"cfbf2df92ce94d5be1db692997a580e41f6ca3a42c23e340d1c621fab10a7138","source":{"kind":"arxiv","id":"2408.07254","version":2},"attestation_state":"computed","paper":{"title":"Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alireza Mousavi-Hosseini, Denny Wu, Murat A. Erdogdu","submitted_at":"2024-08-14T02:13:35Z","abstract_excerpt":"We study the problem of learning multi-index models in high-dimensions using a two-layer neural network trained with the mean-field Langevin algorithm. Under mild distributional assumptions on the data, we characterize the effective dimension $d_{\\mathrm{eff}}$ that controls both sample and computational complexity by utilizing the adaptivity of neural networks to latent low-dimensional structures. When the data exhibit such a structure, $d_{\\mathrm{eff}}$ can be significantly smaller than the ambient dimension. We prove that the sample complexity grows almost linearly with $d_{\\mathrm{eff}}$,"},"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":"2408.07254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-08-14T02:13:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0f57545e1ab03eb2f151d27d3d2860f851c1d3f6c023dd801a31778ec3effde8","abstract_canon_sha256":"357d29e731177b647b0cdc3cda5baa25bcdf9833760327bebbfb398ef070bd8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:12.432569Z","signature_b64":"qmQz8WHj43mdP0lEIM//bqTeLmaj1AJg7AM7fTS2KU8wUW+4Eq/Gy4AlcUBD7jAxPib3IywbqEe9me9Lhlb0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfbf2df92ce94d5be1db692997a580e41f6ca3a42c23e340d1c621fab10a7138","last_reissued_at":"2026-07-05T10:40:12.432086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:12.432086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alireza Mousavi-Hosseini, Denny Wu, Murat A. Erdogdu","submitted_at":"2024-08-14T02:13:35Z","abstract_excerpt":"We study the problem of learning multi-index models in high-dimensions using a two-layer neural network trained with the mean-field Langevin algorithm. Under mild distributional assumptions on the data, we characterize the effective dimension $d_{\\mathrm{eff}}$ that controls both sample and computational complexity by utilizing the adaptivity of neural networks to latent low-dimensional structures. When the data exhibit such a structure, $d_{\\mathrm{eff}}$ can be significantly smaller than the ambient dimension. We prove that the sample complexity grows almost linearly with $d_{\\mathrm{eff}}$,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07254","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/2408.07254/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":"2408.07254","created_at":"2026-07-05T10:40:12.432143+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.07254v2","created_at":"2026-07-05T10:40:12.432143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07254","created_at":"2026-07-05T10:40:12.432143+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z67S36JM5FGV","created_at":"2026-07-05T10:40:12.432143+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z67S36JM5FGVXYO3","created_at":"2026-07-05T10:40:12.432143+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z67S36JM","created_at":"2026-07-05T10:40:12.432143+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22010","citing_title":"Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z67S36JM5FGVXYO3NEUZPJMA4Q","json":"https://pith.science/pith/Z67S36JM5FGVXYO3NEUZPJMA4Q.json","graph_json":"https://pith.science/api/pith-number/Z67S36JM5FGVXYO3NEUZPJMA4Q/graph.json","events_json":"https://pith.science/api/pith-number/Z67S36JM5FGVXYO3NEUZPJMA4Q/events.json","paper":"https://pith.science/paper/Z67S36JM"},"agent_actions":{"view_html":"https://pith.science/pith/Z67S36JM5FGVXYO3NEUZPJMA4Q","download_json":"https://pith.science/pith/Z67S36JM5FGVXYO3NEUZPJMA4Q.json","view_paper":"https://pith.science/paper/Z67S36JM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.07254&json=true","fetch_graph":"https://pith.science/api/pith-number/Z67S36JM5FGVXYO3NEUZPJMA4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/Z67S36JM5FGVXYO3NEUZPJMA4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z67S36JM5FGVXYO3NEUZPJMA4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z67S36JM5FGVXYO3NEUZPJMA4Q/action/storage_attestation","attest_author":"https://pith.science/pith/Z67S36JM5FGVXYO3NEUZPJMA4Q/action/author_attestation","sign_citation":"https://pith.science/pith/Z67S36JM5FGVXYO3NEUZPJMA4Q/action/citation_signature","submit_replication":"https://pith.science/pith/Z67S36JM5FGVXYO3NEUZPJMA4Q/action/replication_record"}},"created_at":"2026-07-05T10:40:12.432143+00:00","updated_at":"2026-07-05T10:40:12.432143+00:00"}