{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LQKLTXG3ZY55GEYPJ74EQRTAJO","short_pith_number":"pith:LQKLTXG3","schema_version":"1.0","canonical_sha256":"5c14b9dcdbce3bd3130f4ff84846604baf0b83b8623d7b2cb22b9c6acc53b473","source":{"kind":"arxiv","id":"1906.00425","version":3},"attestation_state":"computed","paper":{"title":"The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Jacobs, Ronen Basri, Shira Kritchman, Yoni Kasten","submitted_at":"2019-06-02T15:28:28Z","abstract_excerpt":"We study the relationship between the frequency of a function and the speed at which a neural network learns it. We build on recent results that show that the dynamics of overparameterized neural networks trained with gradient descent can be well approximated by a linear system. When normalized training data is uniformly distributed on a hypersphere, the eigenfunctions of this linear system are spherical harmonic functions. We derive the corresponding eigenvalues for each frequency after introducing a bias term in the model. This bias term had been omitted from the linear network model without"},"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":"1906.00425","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-02T15:28:28Z","cross_cats_sorted":["eess.SP","stat.ML"],"title_canon_sha256":"be5c3d2a6e2b1b2ab405f1202df1a20287c3e915ea0ac2a77447b9e093a80032","abstract_canon_sha256":"fddbfb0e948cbe6805d5f7f023cf732fb70b8a8dd414333ecda1895bfcf574fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:05.330890Z","signature_b64":"sZyT3lWiy7rzohOdLCHTHp+V0ngKlZt08oq80FQfItjqiPnIvcxg/j3CwvCOBmjz1kFrkqZXKpuxgDDSwOnvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c14b9dcdbce3bd3130f4ff84846604baf0b83b8623d7b2cb22b9c6acc53b473","last_reissued_at":"2026-07-05T00:23:05.330334Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:05.330334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Jacobs, Ronen Basri, Shira Kritchman, Yoni Kasten","submitted_at":"2019-06-02T15:28:28Z","abstract_excerpt":"We study the relationship between the frequency of a function and the speed at which a neural network learns it. We build on recent results that show that the dynamics of overparameterized neural networks trained with gradient descent can be well approximated by a linear system. When normalized training data is uniformly distributed on a hypersphere, the eigenfunctions of this linear system are spherical harmonic functions. We derive the corresponding eigenvalues for each frequency after introducing a bias term in the model. This bias term had been omitted from the linear network model without"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00425","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/1906.00425/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":"1906.00425","created_at":"2026-07-05T00:23:05.330397+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.00425v3","created_at":"2026-07-05T00:23:05.330397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00425","created_at":"2026-07-05T00:23:05.330397+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQKLTXG3ZY55","created_at":"2026-07-05T00:23:05.330397+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQKLTXG3ZY55GEYP","created_at":"2026-07-05T00:23:05.330397+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQKLTXG3","created_at":"2026-07-05T00:23:05.330397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06949","citing_title":"SpiS-GAN: Spiral-Modulated Handwriting Synthesis with Star Operation","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18686","citing_title":"Neural Spectral Bias and Conformal Correlators I: Introduction and Applications","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQKLTXG3ZY55GEYPJ74EQRTAJO","json":"https://pith.science/pith/LQKLTXG3ZY55GEYPJ74EQRTAJO.json","graph_json":"https://pith.science/api/pith-number/LQKLTXG3ZY55GEYPJ74EQRTAJO/graph.json","events_json":"https://pith.science/api/pith-number/LQKLTXG3ZY55GEYPJ74EQRTAJO/events.json","paper":"https://pith.science/paper/LQKLTXG3"},"agent_actions":{"view_html":"https://pith.science/pith/LQKLTXG3ZY55GEYPJ74EQRTAJO","download_json":"https://pith.science/pith/LQKLTXG3ZY55GEYPJ74EQRTAJO.json","view_paper":"https://pith.science/paper/LQKLTXG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.00425&json=true","fetch_graph":"https://pith.science/api/pith-number/LQKLTXG3ZY55GEYPJ74EQRTAJO/graph.json","fetch_events":"https://pith.science/api/pith-number/LQKLTXG3ZY55GEYPJ74EQRTAJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQKLTXG3ZY55GEYPJ74EQRTAJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQKLTXG3ZY55GEYPJ74EQRTAJO/action/storage_attestation","attest_author":"https://pith.science/pith/LQKLTXG3ZY55GEYPJ74EQRTAJO/action/author_attestation","sign_citation":"https://pith.science/pith/LQKLTXG3ZY55GEYPJ74EQRTAJO/action/citation_signature","submit_replication":"https://pith.science/pith/LQKLTXG3ZY55GEYPJ74EQRTAJO/action/replication_record"}},"created_at":"2026-07-05T00:23:05.330397+00:00","updated_at":"2026-07-05T00:23:05.330397+00:00"}