{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WQIE22YALQBTKJOJBWXR7UWBI6","short_pith_number":"pith:WQIE22YA","schema_version":"1.0","canonical_sha256":"b4104d6b005c033525c90daf1fd2c147aed2df7a4bfbff7f81165b2a1ac29c47","source":{"kind":"arxiv","id":"2403.15749","version":2},"attestation_state":"computed","paper":{"title":"Horoballs and the subgradient method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.LG"],"primary_cat":"math.OC","authors_text":"Adriana Nicolae, Adrian S. Lewis, Genaro Lopez-Acedo","submitted_at":"2024-03-23T07:34:18Z","abstract_excerpt":"To explore convex optimization on Hadamard spaces, we consider an iteration in the style of a subgradient algorithm. Traditionally, such methods assume that the underlying spaces are manifolds and that the objectives are geodesically convex: the methods are described using tangent spaces and exponential maps. By contrast, our iteration applies in a general Hadamard space, is framed in the underlying space itself, and relies instead on horospherical convexity of the objective level sets. For this restricted class of objectives, we prove a complexity result of the usual form. Notably, the comple"},"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":"2403.15749","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-03-23T07:34:18Z","cross_cats_sorted":["cs.CC","cs.LG"],"title_canon_sha256":"86a3494ae18b9b73ec3bc2a3166289d3afa786b85e99b8b1147da41a915581a2","abstract_canon_sha256":"7914bce87f23368dda822a06d64e045095cd1be05ddb96d27f8b69f103d64d6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:50.573135Z","signature_b64":"p24pWkGKjisGUM4+I5WPi0rSb8MSohOumolczwX14XSTIXRS5YFPG0QeALDtjH7zKIBUNjd7NBDIgOSFZ9S+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4104d6b005c033525c90daf1fd2c147aed2df7a4bfbff7f81165b2a1ac29c47","last_reissued_at":"2026-07-05T08:03:50.572685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:50.572685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Horoballs and the subgradient method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.LG"],"primary_cat":"math.OC","authors_text":"Adriana Nicolae, Adrian S. Lewis, Genaro Lopez-Acedo","submitted_at":"2024-03-23T07:34:18Z","abstract_excerpt":"To explore convex optimization on Hadamard spaces, we consider an iteration in the style of a subgradient algorithm. Traditionally, such methods assume that the underlying spaces are manifolds and that the objectives are geodesically convex: the methods are described using tangent spaces and exponential maps. By contrast, our iteration applies in a general Hadamard space, is framed in the underlying space itself, and relies instead on horospherical convexity of the objective level sets. For this restricted class of objectives, we prove a complexity result of the usual form. Notably, the comple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15749","kind":"arxiv","version":2},"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/2403.15749/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":"2403.15749","created_at":"2026-07-05T08:03:50.572742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15749v2","created_at":"2026-07-05T08:03:50.572742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15749","created_at":"2026-07-05T08:03:50.572742+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQIE22YALQBT","created_at":"2026-07-05T08:03:50.572742+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQIE22YALQBTKJOJ","created_at":"2026-07-05T08:03:50.572742+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQIE22YA","created_at":"2026-07-05T08:03:50.572742+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16970","citing_title":"Horospherically Convex Optimization on Hadamard Manifolds Part I: Analysis and Algorithms","ref_index":74,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WQIE22YALQBTKJOJBWXR7UWBI6","json":"https://pith.science/pith/WQIE22YALQBTKJOJBWXR7UWBI6.json","graph_json":"https://pith.science/api/pith-number/WQIE22YALQBTKJOJBWXR7UWBI6/graph.json","events_json":"https://pith.science/api/pith-number/WQIE22YALQBTKJOJBWXR7UWBI6/events.json","paper":"https://pith.science/paper/WQIE22YA"},"agent_actions":{"view_html":"https://pith.science/pith/WQIE22YALQBTKJOJBWXR7UWBI6","download_json":"https://pith.science/pith/WQIE22YALQBTKJOJBWXR7UWBI6.json","view_paper":"https://pith.science/paper/WQIE22YA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15749&json=true","fetch_graph":"https://pith.science/api/pith-number/WQIE22YALQBTKJOJBWXR7UWBI6/graph.json","fetch_events":"https://pith.science/api/pith-number/WQIE22YALQBTKJOJBWXR7UWBI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQIE22YALQBTKJOJBWXR7UWBI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQIE22YALQBTKJOJBWXR7UWBI6/action/storage_attestation","attest_author":"https://pith.science/pith/WQIE22YALQBTKJOJBWXR7UWBI6/action/author_attestation","sign_citation":"https://pith.science/pith/WQIE22YALQBTKJOJBWXR7UWBI6/action/citation_signature","submit_replication":"https://pith.science/pith/WQIE22YALQBTKJOJBWXR7UWBI6/action/replication_record"}},"created_at":"2026-07-05T08:03:50.572742+00:00","updated_at":"2026-07-05T08:03:50.572742+00:00"}