{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QPWO5IQL45KFMEXPZLSWFKWGQ5","short_pith_number":"pith:QPWO5IQL","schema_version":"1.0","canonical_sha256":"83eceea20be7545612efcae562aac687499ba800d58b370a9262242e7fdd1387","source":{"kind":"arxiv","id":"1706.04638","version":3},"attestation_state":"computed","paper":{"title":"Proximal Backpropagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Cremers, Michael Moeller, Thomas Frerix, Thomas M\\\"ollenhoff","submitted_at":"2017-06-14T18:59:13Z","abstract_excerpt":"We propose proximal backpropagation (ProxProp) as a novel algorithm that takes implicit instead of explicit gradient steps to update the network parameters during neural network training. Our algorithm is motivated by the step size limitation of explicit gradient descent, which poses an impediment for optimization. ProxProp is developed from a general point of view on the backpropagation algorithm, currently the most common technique to train neural networks via stochastic gradient descent and variants thereof. Specifically, we show that backpropagation of a prediction error is equivalent to s"},"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":"1706.04638","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-14T18:59:13Z","cross_cats_sorted":[],"title_canon_sha256":"cd600d1e7da07180c131a512f4170e765aa6ba040a46e867e28feb7a729a9348","abstract_canon_sha256":"a33c772dfb793760a2904b39ce061d3ca2ae69a0fbbe4425e46a86275ea622a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:59.261350Z","signature_b64":"sCN48N4fjLQtBhW3aWHnZ+LMnJ4dFuL3UWmHEDLj5QaNNBobzo1Gtn12pU68LPO38qZMVkTXqdeH1DE3iV0mBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83eceea20be7545612efcae562aac687499ba800d58b370a9262242e7fdd1387","last_reissued_at":"2026-05-18T00:22:59.260920Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:59.260920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Proximal Backpropagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Cremers, Michael Moeller, Thomas Frerix, Thomas M\\\"ollenhoff","submitted_at":"2017-06-14T18:59:13Z","abstract_excerpt":"We propose proximal backpropagation (ProxProp) as a novel algorithm that takes implicit instead of explicit gradient steps to update the network parameters during neural network training. Our algorithm is motivated by the step size limitation of explicit gradient descent, which poses an impediment for optimization. ProxProp is developed from a general point of view on the backpropagation algorithm, currently the most common technique to train neural networks via stochastic gradient descent and variants thereof. Specifically, we show that backpropagation of a prediction error is equivalent to s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04638","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":""},"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":"1706.04638","created_at":"2026-05-18T00:22:59.260984+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.04638v3","created_at":"2026-05-18T00:22:59.260984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04638","created_at":"2026-05-18T00:22:59.260984+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPWO5IQL45KF","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPWO5IQL45KFMEXP","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPWO5IQL","created_at":"2026-05-18T12:31:39.905425+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/QPWO5IQL45KFMEXPZLSWFKWGQ5","json":"https://pith.science/pith/QPWO5IQL45KFMEXPZLSWFKWGQ5.json","graph_json":"https://pith.science/api/pith-number/QPWO5IQL45KFMEXPZLSWFKWGQ5/graph.json","events_json":"https://pith.science/api/pith-number/QPWO5IQL45KFMEXPZLSWFKWGQ5/events.json","paper":"https://pith.science/paper/QPWO5IQL"},"agent_actions":{"view_html":"https://pith.science/pith/QPWO5IQL45KFMEXPZLSWFKWGQ5","download_json":"https://pith.science/pith/QPWO5IQL45KFMEXPZLSWFKWGQ5.json","view_paper":"https://pith.science/paper/QPWO5IQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.04638&json=true","fetch_graph":"https://pith.science/api/pith-number/QPWO5IQL45KFMEXPZLSWFKWGQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/QPWO5IQL45KFMEXPZLSWFKWGQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPWO5IQL45KFMEXPZLSWFKWGQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPWO5IQL45KFMEXPZLSWFKWGQ5/action/storage_attestation","attest_author":"https://pith.science/pith/QPWO5IQL45KFMEXPZLSWFKWGQ5/action/author_attestation","sign_citation":"https://pith.science/pith/QPWO5IQL45KFMEXPZLSWFKWGQ5/action/citation_signature","submit_replication":"https://pith.science/pith/QPWO5IQL45KFMEXPZLSWFKWGQ5/action/replication_record"}},"created_at":"2026-05-18T00:22:59.260984+00:00","updated_at":"2026-05-18T00:22:59.260984+00:00"}