{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:NHKEJDKMCLJ3JZUBVPWULKGS5N","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"671d44cc634d4862af1d8546edd76971d95cb3311f5d4f93f15d5025899e3c24","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-07T22:15:07Z","title_canon_sha256":"65836f34466f3f27250d4ba0ab8538aaba631dc9b2d8ddec4baeea0a6724adf5"},"schema_version":"1.0","source":{"id":"1810.03218","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03218","created_at":"2026-07-05T04:01:20Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03218v3","created_at":"2026-07-05T04:01:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03218","created_at":"2026-07-05T04:01:20Z"},{"alias_kind":"pith_short_12","alias_value":"NHKEJDKMCLJ3","created_at":"2026-07-05T04:01:20Z"},{"alias_kind":"pith_short_16","alias_value":"NHKEJDKMCLJ3JZUB","created_at":"2026-07-05T04:01:20Z"},{"alias_kind":"pith_short_8","alias_value":"NHKEJDKM","created_at":"2026-07-05T04:01:20Z"}],"graph_snapshots":[{"event_id":"sha256:e8a42d9ce9221c9e2fce3d56f59a50765c9d662c7449adc9938ac99c64fabee5","target":"graph","created_at":"2026-07-05T04:01:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1810.03218/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Daniel Bienstock, Gonzalo Mu\\~noz, Sebastian Pokutta","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-07T22:15:07Z","title":"Principled Deep Neural Network Training through Linear Programming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03218","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8a0fcb6e52b503ca4eb7a7c017bc6262b6ec676646b1dc691956fd19340b601f","target":"record","created_at":"2026-07-05T04:01:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"671d44cc634d4862af1d8546edd76971d95cb3311f5d4f93f15d5025899e3c24","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-07T22:15:07Z","title_canon_sha256":"65836f34466f3f27250d4ba0ab8538aaba631dc9b2d8ddec4baeea0a6724adf5"},"schema_version":"1.0","source":{"id":"1810.03218","kind":"arxiv","version":3}},"canonical_sha256":"69d4448d4c12d3b4e681abed45a8d2eb515930a31cc2a681809a502747282fe0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69d4448d4c12d3b4e681abed45a8d2eb515930a31cc2a681809a502747282fe0","first_computed_at":"2026-07-05T04:01:20.437205Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:01:20.437205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"69MCmLjSa5yYAnMIrhC+rA1tYtuOhecVgLbBrOh9oANLeE0nAOHrSdyUZKWRVO3xT1s4j2EyOFvTc4Zbgc0tAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:01:20.437664Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.03218","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a0fcb6e52b503ca4eb7a7c017bc6262b6ec676646b1dc691956fd19340b601f","sha256:e8a42d9ce9221c9e2fce3d56f59a50765c9d662c7449adc9938ac99c64fabee5"],"state_sha256":"6dcea39652987dbd030b08d388b9315d65a41f5ad10f7794ef6fda9a497b4682"}