{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BBQMGSUYC3XOG5VC3NSDOXQG2B","short_pith_number":"pith:BBQMGSUY","schema_version":"1.0","canonical_sha256":"0860c34a9816eee376a2db64375e06d075541cccf047ad4cbf5b9f5bfe4fae1a","source":{"kind":"arxiv","id":"2305.07810","version":1},"attestation_state":"computed","paper":{"title":"Depth Dependence of $\\mu$P Learning Rates in ReLU MLPs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Boris Hanin, Samy Jelassi, Sanjiv Kumar, Sashank J. Reddi, Srinadh Bhojanapalli, Ziwei Ji","submitted_at":"2023-05-13T01:10:49Z","abstract_excerpt":"In this short note we consider random fully connected ReLU networks of width $n$ and depth $L$ equipped with a mean-field weight initialization. Our purpose is to study the dependence on $n$ and $L$ of the maximal update ($\\mu$P) learning rate, the largest learning rate for which the mean squared change in pre-activations after one step of gradient descent remains uniformly bounded at large $n,L$. As in prior work on $\\mu$P of Yang et. al., we find that this maximal update learning rate is independent of $n$ for all but the first and last layer weights. However, we find that it has a non-trivi"},"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":"2305.07810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-13T01:10:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ec67ca71010f4120068051eeba7cf12f4d5728cebcf8acc72e04299b59096f14","abstract_canon_sha256":"1b3b0a87345bfc1810f1bfc0c6193f025c45b893b80c23decab10b122a8f24b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:54.229240Z","signature_b64":"YGtwhNb+BRiBkvvMr2wu/Ktk3HPRJ7h+Qu+Xl8iBqC/R4wiC5s0U8xJOXg98liKQlffa+15jnknaFxdSO/jPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0860c34a9816eee376a2db64375e06d075541cccf047ad4cbf5b9f5bfe4fae1a","last_reissued_at":"2026-07-05T06:09:54.228916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:54.228916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Depth Dependence of $\\mu$P Learning Rates in ReLU MLPs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Boris Hanin, Samy Jelassi, Sanjiv Kumar, Sashank J. Reddi, Srinadh Bhojanapalli, Ziwei Ji","submitted_at":"2023-05-13T01:10:49Z","abstract_excerpt":"In this short note we consider random fully connected ReLU networks of width $n$ and depth $L$ equipped with a mean-field weight initialization. Our purpose is to study the dependence on $n$ and $L$ of the maximal update ($\\mu$P) learning rate, the largest learning rate for which the mean squared change in pre-activations after one step of gradient descent remains uniformly bounded at large $n,L$. As in prior work on $\\mu$P of Yang et. al., we find that this maximal update learning rate is independent of $n$ for all but the first and last layer weights. However, we find that it has a non-trivi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07810","kind":"arxiv","version":1},"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/2305.07810/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":"2305.07810","created_at":"2026-07-05T06:09:54.228965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.07810v1","created_at":"2026-07-05T06:09:54.228965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07810","created_at":"2026-07-05T06:09:54.228965+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBQMGSUYC3XO","created_at":"2026-07-05T06:09:54.228965+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBQMGSUYC3XOG5VC","created_at":"2026-07-05T06:09:54.228965+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBQMGSUY","created_at":"2026-07-05T06:09:54.228965+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BBQMGSUYC3XOG5VC3NSDOXQG2B","json":"https://pith.science/pith/BBQMGSUYC3XOG5VC3NSDOXQG2B.json","graph_json":"https://pith.science/api/pith-number/BBQMGSUYC3XOG5VC3NSDOXQG2B/graph.json","events_json":"https://pith.science/api/pith-number/BBQMGSUYC3XOG5VC3NSDOXQG2B/events.json","paper":"https://pith.science/paper/BBQMGSUY"},"agent_actions":{"view_html":"https://pith.science/pith/BBQMGSUYC3XOG5VC3NSDOXQG2B","download_json":"https://pith.science/pith/BBQMGSUYC3XOG5VC3NSDOXQG2B.json","view_paper":"https://pith.science/paper/BBQMGSUY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.07810&json=true","fetch_graph":"https://pith.science/api/pith-number/BBQMGSUYC3XOG5VC3NSDOXQG2B/graph.json","fetch_events":"https://pith.science/api/pith-number/BBQMGSUYC3XOG5VC3NSDOXQG2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBQMGSUYC3XOG5VC3NSDOXQG2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBQMGSUYC3XOG5VC3NSDOXQG2B/action/storage_attestation","attest_author":"https://pith.science/pith/BBQMGSUYC3XOG5VC3NSDOXQG2B/action/author_attestation","sign_citation":"https://pith.science/pith/BBQMGSUYC3XOG5VC3NSDOXQG2B/action/citation_signature","submit_replication":"https://pith.science/pith/BBQMGSUYC3XOG5VC3NSDOXQG2B/action/replication_record"}},"created_at":"2026-07-05T06:09:54.228965+00:00","updated_at":"2026-07-05T06:09:54.228965+00:00"}