{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NHKEJDKMCLJ3JZUBVPWULKGS5N","short_pith_number":"pith:NHKEJDKM","schema_version":"1.0","canonical_sha256":"69d4448d4c12d3b4e681abed45a8d2eb515930a31cc2a681809a502747282fe0","source":{"kind":"arxiv","id":"1810.03218","version":3},"attestation_state":"computed","paper":{"title":"Principled Deep Neural Network Training through Linear Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Bienstock, Gonzalo Mu\\~noz, Sebastian Pokutta","submitted_at":"2018-10-07T22:15:07Z","abstract_excerpt":"Deep learning has received much attention lately due to the impressive empirical performance achieved by training algorithms. Consequently, a need for a better theoretical understanding of these problems has become more evident in recent years. In this work, using a unified framework, we show that there exists a polyhedron which encodes simultaneously all possible deep neural network training problems that can arise from a given architecture, activation functions, loss function, and sample-size. Notably, the size of the polyhedral representation depends only linearly on the sample-size, and a "},"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":"1810.03218","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-07T22:15:07Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"65836f34466f3f27250d4ba0ab8538aaba631dc9b2d8ddec4baeea0a6724adf5","abstract_canon_sha256":"671d44cc634d4862af1d8546edd76971d95cb3311f5d4f93f15d5025899e3c24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:20.437664Z","signature_b64":"69MCmLjSa5yYAnMIrhC+rA1tYtuOhecVgLbBrOh9oANLeE0nAOHrSdyUZKWRVO3xT1s4j2EyOFvTc4Zbgc0tAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69d4448d4c12d3b4e681abed45a8d2eb515930a31cc2a681809a502747282fe0","last_reissued_at":"2026-07-05T04:01:20.437205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:20.437205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Principled Deep Neural Network Training through Linear Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Bienstock, Gonzalo Mu\\~noz, Sebastian Pokutta","submitted_at":"2018-10-07T22:15:07Z","abstract_excerpt":"Deep learning has received much attention lately due to the impressive empirical performance achieved by training algorithms. Consequently, a need for a better theoretical understanding of these problems has become more evident in recent years. In this work, using a unified framework, we show that there exists a polyhedron which encodes simultaneously all possible deep neural network training problems that can arise from a given architecture, activation functions, loss function, and sample-size. Notably, the size of the polyhedral representation depends only linearly on the sample-size, and a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03218","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1810.03218/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":"1810.03218","created_at":"2026-07-05T04:01:20.437279+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.03218v3","created_at":"2026-07-05T04:01:20.437279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03218","created_at":"2026-07-05T04:01:20.437279+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHKEJDKMCLJ3","created_at":"2026-07-05T04:01:20.437279+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHKEJDKMCLJ3JZUB","created_at":"2026-07-05T04:01:20.437279+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHKEJDKM","created_at":"2026-07-05T04:01:20.437279+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/NHKEJDKMCLJ3JZUBVPWULKGS5N","json":"https://pith.science/pith/NHKEJDKMCLJ3JZUBVPWULKGS5N.json","graph_json":"https://pith.science/api/pith-number/NHKEJDKMCLJ3JZUBVPWULKGS5N/graph.json","events_json":"https://pith.science/api/pith-number/NHKEJDKMCLJ3JZUBVPWULKGS5N/events.json","paper":"https://pith.science/paper/NHKEJDKM"},"agent_actions":{"view_html":"https://pith.science/pith/NHKEJDKMCLJ3JZUBVPWULKGS5N","download_json":"https://pith.science/pith/NHKEJDKMCLJ3JZUBVPWULKGS5N.json","view_paper":"https://pith.science/paper/NHKEJDKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.03218&json=true","fetch_graph":"https://pith.science/api/pith-number/NHKEJDKMCLJ3JZUBVPWULKGS5N/graph.json","fetch_events":"https://pith.science/api/pith-number/NHKEJDKMCLJ3JZUBVPWULKGS5N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHKEJDKMCLJ3JZUBVPWULKGS5N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHKEJDKMCLJ3JZUBVPWULKGS5N/action/storage_attestation","attest_author":"https://pith.science/pith/NHKEJDKMCLJ3JZUBVPWULKGS5N/action/author_attestation","sign_citation":"https://pith.science/pith/NHKEJDKMCLJ3JZUBVPWULKGS5N/action/citation_signature","submit_replication":"https://pith.science/pith/NHKEJDKMCLJ3JZUBVPWULKGS5N/action/replication_record"}},"created_at":"2026-07-05T04:01:20.437279+00:00","updated_at":"2026-07-05T04:01:20.437279+00:00"}