{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4PTPJDP5JZUY7ZUV6UI6KBYFYB","short_pith_number":"pith:4PTPJDP5","schema_version":"1.0","canonical_sha256":"e3e6f48dfd4e698fe695f511e50705c04b57ffacce6c513f2174eb7b14fc1ddd","source":{"kind":"arxiv","id":"1707.05023","version":1},"attestation_state":"computed","paper":{"title":"Optimization by gradient boosting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.TH"],"primary_cat":"math.ST","authors_text":"Beno\\^it Cadre (ENS Rennes, G\\'erard Biau (LSTA, IRMAR), LPMA)","submitted_at":"2017-07-17T07:44:26Z","abstract_excerpt":"Gradient boosting is a state-of-the-art prediction technique that sequentially produces a model in the form of linear combinations of simple predictors---typically decision trees---by solving an infinite-dimensional convex optimization problem. We provide in the present paper a thorough analysis of two widespread versions of gradient boosting, and introduce a general framework for studying these algorithms from the point of view of functional optimization. We prove their convergence as the number of iterations tends to infinity and highlight the importance of having a strongly convex risk func"},"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":"1707.05023","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2017-07-17T07:44:26Z","cross_cats_sorted":["cs.LG","stat.TH"],"title_canon_sha256":"32bb26b9d68bfb5fab2a357bbc5f6393ccb4bb07ce7016b1e39cbd94b1484bb7","abstract_canon_sha256":"63f299f1a47b8d933ba8e5cdc06e3c7628e3b9000f8287d90481f7cdacd4debc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:11.581286Z","signature_b64":"BFAm07zVb6HNAplE8mhrMwASAHw7inSgd3urrgrXMjl2ZgkWufMHQDQnN/zAsEwXNt1l1sucDPX6AjJjIvxaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3e6f48dfd4e698fe695f511e50705c04b57ffacce6c513f2174eb7b14fc1ddd","last_reissued_at":"2026-05-18T00:40:11.580695Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:11.580695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimization by gradient boosting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.TH"],"primary_cat":"math.ST","authors_text":"Beno\\^it Cadre (ENS Rennes, G\\'erard Biau (LSTA, IRMAR), LPMA)","submitted_at":"2017-07-17T07:44:26Z","abstract_excerpt":"Gradient boosting is a state-of-the-art prediction technique that sequentially produces a model in the form of linear combinations of simple predictors---typically decision trees---by solving an infinite-dimensional convex optimization problem. We provide in the present paper a thorough analysis of two widespread versions of gradient boosting, and introduce a general framework for studying these algorithms from the point of view of functional optimization. We prove their convergence as the number of iterations tends to infinity and highlight the importance of having a strongly convex risk func"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.05023","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":"1707.05023","created_at":"2026-05-18T00:40:11.580793+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.05023v1","created_at":"2026-05-18T00:40:11.580793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.05023","created_at":"2026-05-18T00:40:11.580793+00:00"},{"alias_kind":"pith_short_12","alias_value":"4PTPJDP5JZUY","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"4PTPJDP5JZUY7ZUV","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"4PTPJDP5","created_at":"2026-05-18T12:31:00.734936+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/4PTPJDP5JZUY7ZUV6UI6KBYFYB","json":"https://pith.science/pith/4PTPJDP5JZUY7ZUV6UI6KBYFYB.json","graph_json":"https://pith.science/api/pith-number/4PTPJDP5JZUY7ZUV6UI6KBYFYB/graph.json","events_json":"https://pith.science/api/pith-number/4PTPJDP5JZUY7ZUV6UI6KBYFYB/events.json","paper":"https://pith.science/paper/4PTPJDP5"},"agent_actions":{"view_html":"https://pith.science/pith/4PTPJDP5JZUY7ZUV6UI6KBYFYB","download_json":"https://pith.science/pith/4PTPJDP5JZUY7ZUV6UI6KBYFYB.json","view_paper":"https://pith.science/paper/4PTPJDP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.05023&json=true","fetch_graph":"https://pith.science/api/pith-number/4PTPJDP5JZUY7ZUV6UI6KBYFYB/graph.json","fetch_events":"https://pith.science/api/pith-number/4PTPJDP5JZUY7ZUV6UI6KBYFYB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4PTPJDP5JZUY7ZUV6UI6KBYFYB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4PTPJDP5JZUY7ZUV6UI6KBYFYB/action/storage_attestation","attest_author":"https://pith.science/pith/4PTPJDP5JZUY7ZUV6UI6KBYFYB/action/author_attestation","sign_citation":"https://pith.science/pith/4PTPJDP5JZUY7ZUV6UI6KBYFYB/action/citation_signature","submit_replication":"https://pith.science/pith/4PTPJDP5JZUY7ZUV6UI6KBYFYB/action/replication_record"}},"created_at":"2026-05-18T00:40:11.580793+00:00","updated_at":"2026-05-18T00:40:11.580793+00:00"}