{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MHHKQLEPUCDXWCZSVJQ5HLDQEU","short_pith_number":"pith:MHHKQLEP","schema_version":"1.0","canonical_sha256":"61cea82c8fa0877b0b32aa61d3ac70250a2d727459b9dce00272ecedcbd3705e","source":{"kind":"arxiv","id":"1906.11985","version":3},"attestation_state":"computed","paper":{"title":"Near-Optimal Methods for Minimizing Star-Convex Functions and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.DS","cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Aaron Sidford, Nimit S. Sohoni, Oliver Hinder","submitted_at":"2019-06-27T22:39:35Z","abstract_excerpt":"In this paper, we provide near-optimal accelerated first-order methods for minimizing a broad class of smooth nonconvex functions that are strictly unimodal on all lines through a minimizer. This function class, which we call the class of smooth quasar-convex functions, is parameterized by a constant $\\gamma \\in (0,1]$, where $\\gamma = 1$ encompasses the classes of smooth convex and star-convex functions, and smaller values of $\\gamma$ indicate that the function can be \"more nonconvex.\" We develop a variant of accelerated gradient descent that computes an $\\epsilon$-approximate minimizer of 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":"1906.11985","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-06-27T22:39:35Z","cross_cats_sorted":["cs.CC","cs.DS","cs.LG","stat.ML"],"title_canon_sha256":"5d0fd9f6144f2d20560ebd9ff25077fbb84630d364b90772d109f44455bcb749","abstract_canon_sha256":"53d37cf4b0cd19eea4d7ba7735e968d15099f82549f72e4bd98dc886d489fd8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:02.067684Z","signature_b64":"Mj8cIT25yfje4GoB3abkUZbsu96nG3taM8GOuyS44OWmKr+NBRWmSGFJRWVU7TlmPYtxBroltyKP9iFFnrrKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61cea82c8fa0877b0b32aa61d3ac70250a2d727459b9dce00272ecedcbd3705e","last_reissued_at":"2026-07-05T05:45:02.067088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:02.067088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near-Optimal Methods for Minimizing Star-Convex Functions and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.DS","cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Aaron Sidford, Nimit S. Sohoni, Oliver Hinder","submitted_at":"2019-06-27T22:39:35Z","abstract_excerpt":"In this paper, we provide near-optimal accelerated first-order methods for minimizing a broad class of smooth nonconvex functions that are strictly unimodal on all lines through a minimizer. This function class, which we call the class of smooth quasar-convex functions, is parameterized by a constant $\\gamma \\in (0,1]$, where $\\gamma = 1$ encompasses the classes of smooth convex and star-convex functions, and smaller values of $\\gamma$ indicate that the function can be \"more nonconvex.\" We develop a variant of accelerated gradient descent that computes an $\\epsilon$-approximate minimizer of a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11985","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/1906.11985/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":"1906.11985","created_at":"2026-07-05T05:45:02.067175+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.11985v3","created_at":"2026-07-05T05:45:02.067175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11985","created_at":"2026-07-05T05:45:02.067175+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHHKQLEPUCDX","created_at":"2026-07-05T05:45:02.067175+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHHKQLEPUCDXWCZS","created_at":"2026-07-05T05:45:02.067175+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHHKQLEP","created_at":"2026-07-05T05:45:02.067175+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02002","citing_title":"The Ball-Proximal (=\"Broximal\") Point Method: a New Algorithm, Convergence Theory, and Applications","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MHHKQLEPUCDXWCZSVJQ5HLDQEU","json":"https://pith.science/pith/MHHKQLEPUCDXWCZSVJQ5HLDQEU.json","graph_json":"https://pith.science/api/pith-number/MHHKQLEPUCDXWCZSVJQ5HLDQEU/graph.json","events_json":"https://pith.science/api/pith-number/MHHKQLEPUCDXWCZSVJQ5HLDQEU/events.json","paper":"https://pith.science/paper/MHHKQLEP"},"agent_actions":{"view_html":"https://pith.science/pith/MHHKQLEPUCDXWCZSVJQ5HLDQEU","download_json":"https://pith.science/pith/MHHKQLEPUCDXWCZSVJQ5HLDQEU.json","view_paper":"https://pith.science/paper/MHHKQLEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.11985&json=true","fetch_graph":"https://pith.science/api/pith-number/MHHKQLEPUCDXWCZSVJQ5HLDQEU/graph.json","fetch_events":"https://pith.science/api/pith-number/MHHKQLEPUCDXWCZSVJQ5HLDQEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHHKQLEPUCDXWCZSVJQ5HLDQEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHHKQLEPUCDXWCZSVJQ5HLDQEU/action/storage_attestation","attest_author":"https://pith.science/pith/MHHKQLEPUCDXWCZSVJQ5HLDQEU/action/author_attestation","sign_citation":"https://pith.science/pith/MHHKQLEPUCDXWCZSVJQ5HLDQEU/action/citation_signature","submit_replication":"https://pith.science/pith/MHHKQLEPUCDXWCZSVJQ5HLDQEU/action/replication_record"}},"created_at":"2026-07-05T05:45:02.067175+00:00","updated_at":"2026-07-05T05:45:02.067175+00:00"}