{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EUH6XPOCAIGKFMMJNWUXES5ATP","short_pith_number":"pith:EUH6XPOC","schema_version":"1.0","canonical_sha256":"250febbdc2020ca2b1896da9724ba09bd45b8d4deddbb5b688e8c17fabe7fa5f","source":{"kind":"arxiv","id":"1805.00915","version":3},"attestation_state":"computed","paper":{"title":"Trainability and Accuracy of Neural Networks: An Interacting Particle System Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.LG"],"primary_cat":"stat.ML","authors_text":"Eric Vanden-Eijnden, Grant M. Rotskoff","submitted_at":"2018-05-02T17:23:42Z","abstract_excerpt":"Neural networks, a central tool in machine learning, have demonstrated remarkable, high fidelity performance on image recognition and classification tasks. These successes evince an ability to accurately represent high dimensional functions, but rigorous results about the approximation error of neural networks after training are few. Here we establish conditions for global convergence of the standard optimization algorithm used in machine learning applications, stochastic gradient descent (SGD), and quantify the scaling of its error with the size of the network. This is done by reinterpreting "},"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":"1805.00915","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-02T17:23:42Z","cross_cats_sorted":["cond-mat.stat-mech","cs.LG"],"title_canon_sha256":"9e9d030775c099d5011a7c3d594b17efc8c25019067f507b66c1cdbc010b4229","abstract_canon_sha256":"13584fc06940f7fef3b9f6295b73866e10ddee177f9bf264e30f135ccf9d2a4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:09.468066Z","signature_b64":"/olcJ1aIlPietrtUncoNUQffjPk1kD7arUU8gTcyF1X/sWRuMUcWhXDmR2mxDwmtrJ5vtDnOic7TDS8Gqi+ACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"250febbdc2020ca2b1896da9724ba09bd45b8d4deddbb5b688e8c17fabe7fa5f","last_reissued_at":"2026-07-05T05:39:09.467608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:09.467608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trainability and Accuracy of Neural Networks: An Interacting Particle System Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.LG"],"primary_cat":"stat.ML","authors_text":"Eric Vanden-Eijnden, Grant M. Rotskoff","submitted_at":"2018-05-02T17:23:42Z","abstract_excerpt":"Neural networks, a central tool in machine learning, have demonstrated remarkable, high fidelity performance on image recognition and classification tasks. These successes evince an ability to accurately represent high dimensional functions, but rigorous results about the approximation error of neural networks after training are few. Here we establish conditions for global convergence of the standard optimization algorithm used in machine learning applications, stochastic gradient descent (SGD), and quantify the scaling of its error with the size of the network. This is done by reinterpreting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00915","kind":"arxiv","version":3},"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/1805.00915/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":"1805.00915","created_at":"2026-07-05T05:39:09.467658+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.00915v3","created_at":"2026-07-05T05:39:09.467658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00915","created_at":"2026-07-05T05:39:09.467658+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUH6XPOCAIGK","created_at":"2026-07-05T05:39:09.467658+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUH6XPOCAIGKFMMJ","created_at":"2026-07-05T05:39:09.467658+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUH6XPOC","created_at":"2026-07-05T05:39:09.467658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10089","citing_title":"A Theory on Flow Matching with Neural Networks","ref_index":234,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30831","citing_title":"Geometric Dyson Brownian Motions and the Free Log-Normal Limit for a Non-Square Gaussian Matrix Product","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"1907.00485","citing_title":"Robust and Resource Efficient Identification of Two Hidden Layer Neural Networks","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2310.10742","citing_title":"Mean-field limit of particle systems with absorption","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2402.08106","citing_title":"Mirror Descent-Ascent for mean-field min-max problems","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22010","citing_title":"Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2511.02258","citing_title":"Limit Theorems for Stochastic Gradient Descent in High-Dimensional Single-Layer Networks","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2401.01335","citing_title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","ref_index":211,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00229","citing_title":"A unified perspective on fine-tuning and sampling with diffusion and flow models","ref_index":133,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EUH6XPOCAIGKFMMJNWUXES5ATP","json":"https://pith.science/pith/EUH6XPOCAIGKFMMJNWUXES5ATP.json","graph_json":"https://pith.science/api/pith-number/EUH6XPOCAIGKFMMJNWUXES5ATP/graph.json","events_json":"https://pith.science/api/pith-number/EUH6XPOCAIGKFMMJNWUXES5ATP/events.json","paper":"https://pith.science/paper/EUH6XPOC"},"agent_actions":{"view_html":"https://pith.science/pith/EUH6XPOCAIGKFMMJNWUXES5ATP","download_json":"https://pith.science/pith/EUH6XPOCAIGKFMMJNWUXES5ATP.json","view_paper":"https://pith.science/paper/EUH6XPOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.00915&json=true","fetch_graph":"https://pith.science/api/pith-number/EUH6XPOCAIGKFMMJNWUXES5ATP/graph.json","fetch_events":"https://pith.science/api/pith-number/EUH6XPOCAIGKFMMJNWUXES5ATP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUH6XPOCAIGKFMMJNWUXES5ATP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUH6XPOCAIGKFMMJNWUXES5ATP/action/storage_attestation","attest_author":"https://pith.science/pith/EUH6XPOCAIGKFMMJNWUXES5ATP/action/author_attestation","sign_citation":"https://pith.science/pith/EUH6XPOCAIGKFMMJNWUXES5ATP/action/citation_signature","submit_replication":"https://pith.science/pith/EUH6XPOCAIGKFMMJNWUXES5ATP/action/replication_record"}},"created_at":"2026-07-05T05:39:09.467658+00:00","updated_at":"2026-07-05T05:39:09.467658+00:00"}