{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KW2QT3V66PB4KZTTINM6RHAKFG","short_pith_number":"pith:KW2QT3V6","schema_version":"1.0","canonical_sha256":"55b509eebef3c3c566734359e89c0a298217fa799c9fdbcaf196b57e2b1f4490","source":{"kind":"arxiv","id":"1802.09750","version":1},"attestation_state":"computed","paper":{"title":"Train Feedfoward Neural Network with Layer-wise Adaptive Rate via Approximating Back-matching Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Huishuai Zhang, Tie-Yan Liu, Wei Chen","submitted_at":"2018-02-27T07:25:32Z","abstract_excerpt":"Stochastic gradient descent (SGD) has achieved great success in training deep neural network, where the gradient is computed through back-propagation. However, the back-propagated values of different layers vary dramatically. This inconsistence of gradient magnitude across different layers renders optimization of deep neural network with a single learning rate problematic. We introduce the back-matching propagation which computes the backward values on the layer's parameter and the input by matching backward values on the layer's output. This leads to solving a bunch of least-squares problems,"},"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":"1802.09750","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-27T07:25:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4371891e016d5613bd52bcae6a5a5cd4e91b57bcba1c318b35548eb055fb17c2","abstract_canon_sha256":"6704ce30654658f68b48b8e8b9e60268fce37edac7ff03d0435699944ea3a499"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:22.344523Z","signature_b64":"KxW8KmbY6khD17l2O87LT+R4YKyYUieRDEKjSZrZKNWMOiSk7+N4mGprksf/fSbfSIvxlHaZHgB+Gckm9G88DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55b509eebef3c3c566734359e89c0a298217fa799c9fdbcaf196b57e2b1f4490","last_reissued_at":"2026-05-18T00:22:22.343973Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:22.343973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Train Feedfoward Neural Network with Layer-wise Adaptive Rate via Approximating Back-matching Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Huishuai Zhang, Tie-Yan Liu, Wei Chen","submitted_at":"2018-02-27T07:25:32Z","abstract_excerpt":"Stochastic gradient descent (SGD) has achieved great success in training deep neural network, where the gradient is computed through back-propagation. However, the back-propagated values of different layers vary dramatically. This inconsistence of gradient magnitude across different layers renders optimization of deep neural network with a single learning rate problematic. We introduce the back-matching propagation which computes the backward values on the layer's parameter and the input by matching backward values on the layer's output. This leads to solving a bunch of least-squares problems,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09750","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":""},"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":"1802.09750","created_at":"2026-05-18T00:22:22.344030+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.09750v1","created_at":"2026-05-18T00:22:22.344030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09750","created_at":"2026-05-18T00:22:22.344030+00:00"},{"alias_kind":"pith_short_12","alias_value":"KW2QT3V66PB4","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KW2QT3V66PB4KZTT","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KW2QT3V6","created_at":"2026-05-18T12:32:33.847187+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/KW2QT3V66PB4KZTTINM6RHAKFG","json":"https://pith.science/pith/KW2QT3V66PB4KZTTINM6RHAKFG.json","graph_json":"https://pith.science/api/pith-number/KW2QT3V66PB4KZTTINM6RHAKFG/graph.json","events_json":"https://pith.science/api/pith-number/KW2QT3V66PB4KZTTINM6RHAKFG/events.json","paper":"https://pith.science/paper/KW2QT3V6"},"agent_actions":{"view_html":"https://pith.science/pith/KW2QT3V66PB4KZTTINM6RHAKFG","download_json":"https://pith.science/pith/KW2QT3V66PB4KZTTINM6RHAKFG.json","view_paper":"https://pith.science/paper/KW2QT3V6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.09750&json=true","fetch_graph":"https://pith.science/api/pith-number/KW2QT3V66PB4KZTTINM6RHAKFG/graph.json","fetch_events":"https://pith.science/api/pith-number/KW2QT3V66PB4KZTTINM6RHAKFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KW2QT3V66PB4KZTTINM6RHAKFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KW2QT3V66PB4KZTTINM6RHAKFG/action/storage_attestation","attest_author":"https://pith.science/pith/KW2QT3V66PB4KZTTINM6RHAKFG/action/author_attestation","sign_citation":"https://pith.science/pith/KW2QT3V66PB4KZTTINM6RHAKFG/action/citation_signature","submit_replication":"https://pith.science/pith/KW2QT3V66PB4KZTTINM6RHAKFG/action/replication_record"}},"created_at":"2026-05-18T00:22:22.344030+00:00","updated_at":"2026-05-18T00:22:22.344030+00:00"}