{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LF26HRO5PEIGIP2WWBAZTLOLHB","short_pith_number":"pith:LF26HRO5","schema_version":"1.0","canonical_sha256":"5975e3c5dd7910643f56b04199adcb3868079084ab101cfd5650ef8d0a61a0be","source":{"kind":"arxiv","id":"1710.06910","version":2},"attestation_state":"computed","paper":{"title":"Characterization of Gradient Dominance and Regularity Conditions for Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Yingbin Liang, Yi Zhou","submitted_at":"2017-10-18T19:53:57Z","abstract_excerpt":"The past decade has witnessed a successful application of deep learning to solving many challenging problems in machine learning and artificial intelligence. However, the loss functions of deep neural networks (especially nonlinear networks) are still far from being well understood from a theoretical aspect. In this paper, we enrich the current understanding of the landscape of the square loss functions for three types of neural networks. Specifically, when the parameter matrices are square, we provide an explicit characterization of the global minimizers for linear networks, linear residual n"},"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":"1710.06910","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-18T19:53:57Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"28e8d508b33085b6cc62b8b8d48862f828ae141835f9e2076cd328683d7d2a46","abstract_canon_sha256":"0def812f668d89b2fd0f742cf95cfdf0abd9500ed5ce9576b7f7951a959b20fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:25.297485Z","signature_b64":"33BG0zv7Ql+EeIHRBxgivGk4tMv5HTgJgHlRWYLD4XruEnqXjmUz0FYXAyK6UNoGMUGKiPlUlL1GBf3kz2VKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5975e3c5dd7910643f56b04199adcb3868079084ab101cfd5650ef8d0a61a0be","last_reissued_at":"2026-05-18T00:32:25.296811Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:25.296811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Characterization of Gradient Dominance and Regularity Conditions for Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Yingbin Liang, Yi Zhou","submitted_at":"2017-10-18T19:53:57Z","abstract_excerpt":"The past decade has witnessed a successful application of deep learning to solving many challenging problems in machine learning and artificial intelligence. However, the loss functions of deep neural networks (especially nonlinear networks) are still far from being well understood from a theoretical aspect. In this paper, we enrich the current understanding of the landscape of the square loss functions for three types of neural networks. Specifically, when the parameter matrices are square, we provide an explicit characterization of the global minimizers for linear networks, linear residual n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.06910","kind":"arxiv","version":2},"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":"1710.06910","created_at":"2026-05-18T00:32:25.296886+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.06910v2","created_at":"2026-05-18T00:32:25.296886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.06910","created_at":"2026-05-18T00:32:25.296886+00:00"},{"alias_kind":"pith_short_12","alias_value":"LF26HRO5PEIG","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LF26HRO5PEIGIP2W","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LF26HRO5","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06959","citing_title":"Locally Near Optimal Piecewise Linear Regression in High Dimensions via Difference of Max-Affine Functions","ref_index":110,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LF26HRO5PEIGIP2WWBAZTLOLHB","json":"https://pith.science/pith/LF26HRO5PEIGIP2WWBAZTLOLHB.json","graph_json":"https://pith.science/api/pith-number/LF26HRO5PEIGIP2WWBAZTLOLHB/graph.json","events_json":"https://pith.science/api/pith-number/LF26HRO5PEIGIP2WWBAZTLOLHB/events.json","paper":"https://pith.science/paper/LF26HRO5"},"agent_actions":{"view_html":"https://pith.science/pith/LF26HRO5PEIGIP2WWBAZTLOLHB","download_json":"https://pith.science/pith/LF26HRO5PEIGIP2WWBAZTLOLHB.json","view_paper":"https://pith.science/paper/LF26HRO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.06910&json=true","fetch_graph":"https://pith.science/api/pith-number/LF26HRO5PEIGIP2WWBAZTLOLHB/graph.json","fetch_events":"https://pith.science/api/pith-number/LF26HRO5PEIGIP2WWBAZTLOLHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LF26HRO5PEIGIP2WWBAZTLOLHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LF26HRO5PEIGIP2WWBAZTLOLHB/action/storage_attestation","attest_author":"https://pith.science/pith/LF26HRO5PEIGIP2WWBAZTLOLHB/action/author_attestation","sign_citation":"https://pith.science/pith/LF26HRO5PEIGIP2WWBAZTLOLHB/action/citation_signature","submit_replication":"https://pith.science/pith/LF26HRO5PEIGIP2WWBAZTLOLHB/action/replication_record"}},"created_at":"2026-05-18T00:32:25.296886+00:00","updated_at":"2026-05-18T00:32:25.296886+00:00"}