{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:32OXYNT6DH575TPWR6YKVHOFKK","short_pith_number":"pith:32OXYNT6","schema_version":"1.0","canonical_sha256":"de9d7c367e19fbfecdf68fb0aa9dc552875a7bf4fed0f490d70c7e767ad61836","source":{"kind":"arxiv","id":"1902.01843","version":2},"attestation_state":"computed","paper":{"title":"Global convergence of neuron birth-death dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Eric Vanden-Eijnden, Grant Rotskoff, Joan Bruna, Samy Jelassi","submitted_at":"2019-02-05T18:24:10Z","abstract_excerpt":"Neural networks with a large number of parameters admit a mean-field description, which has recently served as a theoretical explanation for the favorable training properties of \"overparameterized\" models. In this regime, gradient descent obeys a deterministic partial differential equation (PDE) that converges to a globally optimal solution for networks with a single hidden layer under appropriate assumptions. In this work, we propose a non-local mass transport dynamics that leads to a modified PDE with the same minimizer. We implement this non-local dynamics as a stochastic neuronal birth-dea"},"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":"1902.01843","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-05T18:24:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8e28a7ced841d8ec4ad54abf66ee5d6d58f9be4080190bdac4c70a9e7f1118e9","abstract_canon_sha256":"463f7488efae5b28ac331a54e4ac5f75c33a3cb464436b5319cd9377d24e33b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:04.552339Z","signature_b64":"k8UYldC3zv5v9jm30+LpbTAB2VJ47CV8dODvbssVJBXSncss1yJZI/e+v/FvZOZU3Z75X2sgk7zjlqJPgucqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de9d7c367e19fbfecdf68fb0aa9dc552875a7bf4fed0f490d70c7e767ad61836","last_reissued_at":"2026-05-17T23:50:04.551833Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:04.551833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global convergence of neuron birth-death dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Eric Vanden-Eijnden, Grant Rotskoff, Joan Bruna, Samy Jelassi","submitted_at":"2019-02-05T18:24:10Z","abstract_excerpt":"Neural networks with a large number of parameters admit a mean-field description, which has recently served as a theoretical explanation for the favorable training properties of \"overparameterized\" models. In this regime, gradient descent obeys a deterministic partial differential equation (PDE) that converges to a globally optimal solution for networks with a single hidden layer under appropriate assumptions. In this work, we propose a non-local mass transport dynamics that leads to a modified PDE with the same minimizer. We implement this non-local dynamics as a stochastic neuronal birth-dea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01843","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":""},"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":"1902.01843","created_at":"2026-05-17T23:50:04.551896+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.01843v2","created_at":"2026-05-17T23:50:04.551896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01843","created_at":"2026-05-17T23:50:04.551896+00:00"},{"alias_kind":"pith_short_12","alias_value":"32OXYNT6DH57","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"32OXYNT6DH575TPW","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"32OXYNT6","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.10600","citing_title":"Weighted quantization using MMD: From mean field to mean shift via gradient flows","ref_index":80,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/32OXYNT6DH575TPWR6YKVHOFKK","json":"https://pith.science/pith/32OXYNT6DH575TPWR6YKVHOFKK.json","graph_json":"https://pith.science/api/pith-number/32OXYNT6DH575TPWR6YKVHOFKK/graph.json","events_json":"https://pith.science/api/pith-number/32OXYNT6DH575TPWR6YKVHOFKK/events.json","paper":"https://pith.science/paper/32OXYNT6"},"agent_actions":{"view_html":"https://pith.science/pith/32OXYNT6DH575TPWR6YKVHOFKK","download_json":"https://pith.science/pith/32OXYNT6DH575TPWR6YKVHOFKK.json","view_paper":"https://pith.science/paper/32OXYNT6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.01843&json=true","fetch_graph":"https://pith.science/api/pith-number/32OXYNT6DH575TPWR6YKVHOFKK/graph.json","fetch_events":"https://pith.science/api/pith-number/32OXYNT6DH575TPWR6YKVHOFKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/32OXYNT6DH575TPWR6YKVHOFKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/32OXYNT6DH575TPWR6YKVHOFKK/action/storage_attestation","attest_author":"https://pith.science/pith/32OXYNT6DH575TPWR6YKVHOFKK/action/author_attestation","sign_citation":"https://pith.science/pith/32OXYNT6DH575TPWR6YKVHOFKK/action/citation_signature","submit_replication":"https://pith.science/pith/32OXYNT6DH575TPWR6YKVHOFKK/action/replication_record"}},"created_at":"2026-05-17T23:50:04.551896+00:00","updated_at":"2026-05-17T23:50:04.551896+00:00"}