{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:5LIAURM4ZYX23V557T3ESQW6JM","short_pith_number":"pith:5LIAURM4","schema_version":"1.0","canonical_sha256":"ead00a459cce2fadd7bdfcf64942de4b2809b771b80ce83750d2be1b14d3d36a","source":{"kind":"arxiv","id":"1610.05708","version":3},"attestation_state":"computed","paper":{"title":"Relatively-Smooth Convex Optimization by First-Order Methods, and Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Haihao Lu, Robert M. Freund, Yurii Nesterov","submitted_at":"2016-10-18T17:05:03Z","abstract_excerpt":"The usual approach to developing and analyzing first-order methods for smooth convex optimization assumes that the gradient of the objective function is uniformly smooth with some Lipschitz constant $L$. However, in many settings the differentiable convex function $f(\\cdot)$ is not uniformly smooth -- for example in $D$-optimal design where $f(x):=-\\ln \\det(HXH^T)$, or even the univariate setting with $f(x) := -\\ln(x) + x^2$. Herein we develop a notion of \"relative smoothness\" and relative strong convexity that is determined relative to a user-specified \"reference function\" $h(\\cdot)$ (that sh"},"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":"1610.05708","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-10-18T17:05:03Z","cross_cats_sorted":[],"title_canon_sha256":"6a1ea54862b9ef0813039b984051493e3498596297bbe70ef39b25801a8a0563","abstract_canon_sha256":"07164466cab4a8d2663a7fe7d742d85c3af32efe008f07c6241161c182835819"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:22.522513Z","signature_b64":"zhmXCef2OOwRu7goS2hZ9+pLx6mdvY7FvylNvC1aXs3agwD1IGQpdR2JLxRSBHmauciaCSD/8O8OT//GVVgjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ead00a459cce2fadd7bdfcf64942de4b2809b771b80ce83750d2be1b14d3d36a","last_reissued_at":"2026-05-18T00:33:22.521772Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:22.521772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relatively-Smooth Convex Optimization by First-Order Methods, and Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Haihao Lu, Robert M. Freund, Yurii Nesterov","submitted_at":"2016-10-18T17:05:03Z","abstract_excerpt":"The usual approach to developing and analyzing first-order methods for smooth convex optimization assumes that the gradient of the objective function is uniformly smooth with some Lipschitz constant $L$. However, in many settings the differentiable convex function $f(\\cdot)$ is not uniformly smooth -- for example in $D$-optimal design where $f(x):=-\\ln \\det(HXH^T)$, or even the univariate setting with $f(x) := -\\ln(x) + x^2$. Herein we develop a notion of \"relative smoothness\" and relative strong convexity that is determined relative to a user-specified \"reference function\" $h(\\cdot)$ (that sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.05708","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":""},"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":"1610.05708","created_at":"2026-05-18T00:33:22.521892+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.05708v3","created_at":"2026-05-18T00:33:22.521892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.05708","created_at":"2026-05-18T00:33:22.521892+00:00"},{"alias_kind":"pith_short_12","alias_value":"5LIAURM4ZYX2","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_16","alias_value":"5LIAURM4ZYX23V55","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_8","alias_value":"5LIAURM4","created_at":"2026-05-18T12:30:01.593930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08946","citing_title":"A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5LIAURM4ZYX23V557T3ESQW6JM","json":"https://pith.science/pith/5LIAURM4ZYX23V557T3ESQW6JM.json","graph_json":"https://pith.science/api/pith-number/5LIAURM4ZYX23V557T3ESQW6JM/graph.json","events_json":"https://pith.science/api/pith-number/5LIAURM4ZYX23V557T3ESQW6JM/events.json","paper":"https://pith.science/paper/5LIAURM4"},"agent_actions":{"view_html":"https://pith.science/pith/5LIAURM4ZYX23V557T3ESQW6JM","download_json":"https://pith.science/pith/5LIAURM4ZYX23V557T3ESQW6JM.json","view_paper":"https://pith.science/paper/5LIAURM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.05708&json=true","fetch_graph":"https://pith.science/api/pith-number/5LIAURM4ZYX23V557T3ESQW6JM/graph.json","fetch_events":"https://pith.science/api/pith-number/5LIAURM4ZYX23V557T3ESQW6JM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5LIAURM4ZYX23V557T3ESQW6JM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5LIAURM4ZYX23V557T3ESQW6JM/action/storage_attestation","attest_author":"https://pith.science/pith/5LIAURM4ZYX23V557T3ESQW6JM/action/author_attestation","sign_citation":"https://pith.science/pith/5LIAURM4ZYX23V557T3ESQW6JM/action/citation_signature","submit_replication":"https://pith.science/pith/5LIAURM4ZYX23V557T3ESQW6JM/action/replication_record"}},"created_at":"2026-05-18T00:33:22.521892+00:00","updated_at":"2026-05-18T00:33:22.521892+00:00"}