{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5NHVYHH5KZ3IAHDGI7BUUHJSJC","short_pith_number":"pith:5NHVYHH5","schema_version":"1.0","canonical_sha256":"eb4f5c1cfd5676801c6647c34a1d324893641d7f165ec57632bccc8914ae7490","source":{"kind":"arxiv","id":"1806.09077","version":4},"attestation_state":"computed","paper":{"title":"Beyond Backprop: Online Alternating Minimization with Auxiliary Variables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Anna Choromanska, Benjamin Cowen, Brian Kingsbury, Djallel Bouneffouf, Irina Rish, Mattia Rigotti, Paolo DiAchille, Ravi Tejwani, Ronny Luss, Sadhana Kumaravel, Viatcheslav Gurev","submitted_at":"2018-06-24T03:55:28Z","abstract_excerpt":"Despite significant recent advances in deep neural networks, training them remains a challenge due to the highly non-convex nature of the objective function. State-of-the-art methods rely on error backpropagation, which suffers from several well-known issues, such as vanishing and exploding gradients, inability to handle non-differentiable nonlinearities and to parallelize weight-updates across layers, and biological implausibility. These limitations continue to motivate exploration of alternative training algorithms, including several recently proposed auxiliary-variable methods which break t"},"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":"1806.09077","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-24T03:55:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a230764ab739f365231f147d9e8ac5bfb95e8418b863e7960c940e260ede2d7c","abstract_canon_sha256":"1af73799d4480611198a361c45e9b1d47893098c813e862a957fedee8b45ec60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:10.155722Z","signature_b64":"opZayLaP3MAIRWmIp8RT30DauTiQgs6J/oQTOYWdIa8hAt7PN6Z1dtGHGYbNQH69TD9LR+OiycfLwO9lRTTUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb4f5c1cfd5676801c6647c34a1d324893641d7f165ec57632bccc8914ae7490","last_reissued_at":"2026-05-17T23:44:10.155044Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:10.155044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Backprop: Online Alternating Minimization with Auxiliary Variables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Anna Choromanska, Benjamin Cowen, Brian Kingsbury, Djallel Bouneffouf, Irina Rish, Mattia Rigotti, Paolo DiAchille, Ravi Tejwani, Ronny Luss, Sadhana Kumaravel, Viatcheslav Gurev","submitted_at":"2018-06-24T03:55:28Z","abstract_excerpt":"Despite significant recent advances in deep neural networks, training them remains a challenge due to the highly non-convex nature of the objective function. State-of-the-art methods rely on error backpropagation, which suffers from several well-known issues, such as vanishing and exploding gradients, inability to handle non-differentiable nonlinearities and to parallelize weight-updates across layers, and biological implausibility. These limitations continue to motivate exploration of alternative training algorithms, including several recently proposed auxiliary-variable methods which break t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.09077","kind":"arxiv","version":4},"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":"1806.09077","created_at":"2026-05-17T23:44:10.155145+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.09077v4","created_at":"2026-05-17T23:44:10.155145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.09077","created_at":"2026-05-17T23:44:10.155145+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NHVYHH5KZ3I","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NHVYHH5KZ3IAHDG","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NHVYHH5","created_at":"2026-05-18T12:32:08.215937+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/5NHVYHH5KZ3IAHDGI7BUUHJSJC","json":"https://pith.science/pith/5NHVYHH5KZ3IAHDGI7BUUHJSJC.json","graph_json":"https://pith.science/api/pith-number/5NHVYHH5KZ3IAHDGI7BUUHJSJC/graph.json","events_json":"https://pith.science/api/pith-number/5NHVYHH5KZ3IAHDGI7BUUHJSJC/events.json","paper":"https://pith.science/paper/5NHVYHH5"},"agent_actions":{"view_html":"https://pith.science/pith/5NHVYHH5KZ3IAHDGI7BUUHJSJC","download_json":"https://pith.science/pith/5NHVYHH5KZ3IAHDGI7BUUHJSJC.json","view_paper":"https://pith.science/paper/5NHVYHH5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.09077&json=true","fetch_graph":"https://pith.science/api/pith-number/5NHVYHH5KZ3IAHDGI7BUUHJSJC/graph.json","fetch_events":"https://pith.science/api/pith-number/5NHVYHH5KZ3IAHDGI7BUUHJSJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NHVYHH5KZ3IAHDGI7BUUHJSJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NHVYHH5KZ3IAHDGI7BUUHJSJC/action/storage_attestation","attest_author":"https://pith.science/pith/5NHVYHH5KZ3IAHDGI7BUUHJSJC/action/author_attestation","sign_citation":"https://pith.science/pith/5NHVYHH5KZ3IAHDGI7BUUHJSJC/action/citation_signature","submit_replication":"https://pith.science/pith/5NHVYHH5KZ3IAHDGI7BUUHJSJC/action/replication_record"}},"created_at":"2026-05-17T23:44:10.155145+00:00","updated_at":"2026-05-17T23:44:10.155145+00:00"}