{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:42CB6WFPOXQYUZ5REQQHKZ6VJB","short_pith_number":"pith:42CB6WFP","schema_version":"1.0","canonical_sha256":"e6841f58af75e18a67b124207567d5487054709eec0f3399fa48c988ca7e4bfb","source":{"kind":"arxiv","id":"1906.01504","version":1},"attestation_state":"computed","paper":{"title":"Embedded hyper-parameter tuning by Simulated Annealing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DM","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Matteo Fischetti, Matteo Stringher","submitted_at":"2019-06-04T15:14:36Z","abstract_excerpt":"We propose a new metaheuristic training scheme that combines Stochastic Gradient Descent (SGD) and Discrete Optimization in an unconventional way. Our idea is to define a discrete neighborhood of the current SGD point containing a number of \"potentially good moves\" that exploit gradient information, and to search this neighborhood by using a classical metaheuristic scheme borrowed from Discrete Optimization.\n  In the present paper we investigate the use of a simple Simulated Annealing (SA) metaheuristic that accepts/rejects a candidate new solution in the neighborhood with a probability that d"},"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":"1906.01504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-04T15:14:36Z","cross_cats_sorted":["cs.AI","cs.DM","math.OC","stat.ML"],"title_canon_sha256":"b3c57a95621e41371b73b0a172d73afd3c57f4184b2e13612e4df54cf113423c","abstract_canon_sha256":"8f4f1d5cce7a3751e9e87aecc89c090fe87bc8b7a19958524cb1e98391c26e2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:16.353243Z","signature_b64":"T/1Rl61huy5qK1RH9rup8TtC63jpwCKuxQrAHajpvVzb813cim5y9X+wE7iijezEaQ3Rz7+lQuSlxpVAhRbLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6841f58af75e18a67b124207567d5487054709eec0f3399fa48c988ca7e4bfb","last_reissued_at":"2026-05-17T23:44:16.352830Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:16.352830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embedded hyper-parameter tuning by Simulated Annealing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DM","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Matteo Fischetti, Matteo Stringher","submitted_at":"2019-06-04T15:14:36Z","abstract_excerpt":"We propose a new metaheuristic training scheme that combines Stochastic Gradient Descent (SGD) and Discrete Optimization in an unconventional way. Our idea is to define a discrete neighborhood of the current SGD point containing a number of \"potentially good moves\" that exploit gradient information, and to search this neighborhood by using a classical metaheuristic scheme borrowed from Discrete Optimization.\n  In the present paper we investigate the use of a simple Simulated Annealing (SA) metaheuristic that accepts/rejects a candidate new solution in the neighborhood with a probability that d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01504","kind":"arxiv","version":1},"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":"1906.01504","created_at":"2026-05-17T23:44:16.352894+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01504v1","created_at":"2026-05-17T23:44:16.352894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01504","created_at":"2026-05-17T23:44:16.352894+00:00"},{"alias_kind":"pith_short_12","alias_value":"42CB6WFPOXQY","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"42CB6WFPOXQYUZ5R","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"42CB6WFP","created_at":"2026-05-18T12:33:10.108867+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/42CB6WFPOXQYUZ5REQQHKZ6VJB","json":"https://pith.science/pith/42CB6WFPOXQYUZ5REQQHKZ6VJB.json","graph_json":"https://pith.science/api/pith-number/42CB6WFPOXQYUZ5REQQHKZ6VJB/graph.json","events_json":"https://pith.science/api/pith-number/42CB6WFPOXQYUZ5REQQHKZ6VJB/events.json","paper":"https://pith.science/paper/42CB6WFP"},"agent_actions":{"view_html":"https://pith.science/pith/42CB6WFPOXQYUZ5REQQHKZ6VJB","download_json":"https://pith.science/pith/42CB6WFPOXQYUZ5REQQHKZ6VJB.json","view_paper":"https://pith.science/paper/42CB6WFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01504&json=true","fetch_graph":"https://pith.science/api/pith-number/42CB6WFPOXQYUZ5REQQHKZ6VJB/graph.json","fetch_events":"https://pith.science/api/pith-number/42CB6WFPOXQYUZ5REQQHKZ6VJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42CB6WFPOXQYUZ5REQQHKZ6VJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42CB6WFPOXQYUZ5REQQHKZ6VJB/action/storage_attestation","attest_author":"https://pith.science/pith/42CB6WFPOXQYUZ5REQQHKZ6VJB/action/author_attestation","sign_citation":"https://pith.science/pith/42CB6WFPOXQYUZ5REQQHKZ6VJB/action/citation_signature","submit_replication":"https://pith.science/pith/42CB6WFPOXQYUZ5REQQHKZ6VJB/action/replication_record"}},"created_at":"2026-05-17T23:44:16.352894+00:00","updated_at":"2026-05-17T23:44:16.352894+00:00"}