{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S2FSNUT6XJDHEGE3OLQKKUO6UK","short_pith_number":"pith:S2FSNUT6","schema_version":"1.0","canonical_sha256":"968b26d27eba4672189b72e0a551dea2aa560e242b42ac3af3518b03dc167163","source":{"kind":"arxiv","id":"2402.05025","version":1},"attestation_state":"computed","paper":{"title":"Strong convexity-guided hyper-parameter optimization for flatter losses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rahul Yedida, Snehanshu Saha","submitted_at":"2024-02-07T16:47:07Z","abstract_excerpt":"We propose a novel white-box approach to hyper-parameter optimization. Motivated by recent work establishing a relationship between flat minima and generalization, we first establish a relationship between the strong convexity of the loss and its flatness. Based on this, we seek to find hyper-parameter configurations that improve flatness by minimizing the strong convexity of the loss. By using the structure of the underlying neural network, we derive closed-form equations to approximate the strong convexity parameter, and attempt to find hyper-parameters that minimize it in a randomized fashi"},"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":"2402.05025","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T16:47:07Z","cross_cats_sorted":[],"title_canon_sha256":"90183f6771c3c85c12337452d595930d42074373a90fa68125a8ecf6d70cba18","abstract_canon_sha256":"66ef4f38610166d95de16657f00518ab34215b379e46f6223f01c767f77ebea0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:35.323337Z","signature_b64":"1P5W6uqNlq1/nYUByBNlACsF85+PqX3wlJfIaAeft7CWzBDKeb/xbLsbaITamjJQrQdBYFgnyOjE3eAvsvwFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"968b26d27eba4672189b72e0a551dea2aa560e242b42ac3af3518b03dc167163","last_reissued_at":"2026-07-05T07:42:35.322899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:35.322899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Strong convexity-guided hyper-parameter optimization for flatter losses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rahul Yedida, Snehanshu Saha","submitted_at":"2024-02-07T16:47:07Z","abstract_excerpt":"We propose a novel white-box approach to hyper-parameter optimization. Motivated by recent work establishing a relationship between flat minima and generalization, we first establish a relationship between the strong convexity of the loss and its flatness. Based on this, we seek to find hyper-parameter configurations that improve flatness by minimizing the strong convexity of the loss. By using the structure of the underlying neural network, we derive closed-form equations to approximate the strong convexity parameter, and attempt to find hyper-parameters that minimize it in a randomized fashi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05025","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.05025/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":"2402.05025","created_at":"2026-07-05T07:42:35.322960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05025v1","created_at":"2026-07-05T07:42:35.322960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05025","created_at":"2026-07-05T07:42:35.322960+00:00"},{"alias_kind":"pith_short_12","alias_value":"S2FSNUT6XJDH","created_at":"2026-07-05T07:42:35.322960+00:00"},{"alias_kind":"pith_short_16","alias_value":"S2FSNUT6XJDHEGE3","created_at":"2026-07-05T07:42:35.322960+00:00"},{"alias_kind":"pith_short_8","alias_value":"S2FSNUT6","created_at":"2026-07-05T07:42:35.322960+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/S2FSNUT6XJDHEGE3OLQKKUO6UK","json":"https://pith.science/pith/S2FSNUT6XJDHEGE3OLQKKUO6UK.json","graph_json":"https://pith.science/api/pith-number/S2FSNUT6XJDHEGE3OLQKKUO6UK/graph.json","events_json":"https://pith.science/api/pith-number/S2FSNUT6XJDHEGE3OLQKKUO6UK/events.json","paper":"https://pith.science/paper/S2FSNUT6"},"agent_actions":{"view_html":"https://pith.science/pith/S2FSNUT6XJDHEGE3OLQKKUO6UK","download_json":"https://pith.science/pith/S2FSNUT6XJDHEGE3OLQKKUO6UK.json","view_paper":"https://pith.science/paper/S2FSNUT6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05025&json=true","fetch_graph":"https://pith.science/api/pith-number/S2FSNUT6XJDHEGE3OLQKKUO6UK/graph.json","fetch_events":"https://pith.science/api/pith-number/S2FSNUT6XJDHEGE3OLQKKUO6UK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S2FSNUT6XJDHEGE3OLQKKUO6UK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S2FSNUT6XJDHEGE3OLQKKUO6UK/action/storage_attestation","attest_author":"https://pith.science/pith/S2FSNUT6XJDHEGE3OLQKKUO6UK/action/author_attestation","sign_citation":"https://pith.science/pith/S2FSNUT6XJDHEGE3OLQKKUO6UK/action/citation_signature","submit_replication":"https://pith.science/pith/S2FSNUT6XJDHEGE3OLQKKUO6UK/action/replication_record"}},"created_at":"2026-07-05T07:42:35.322960+00:00","updated_at":"2026-07-05T07:42:35.322960+00:00"}