{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4NXBYYNHRTXXM3CYJDF3AXIDHQ","short_pith_number":"pith:4NXBYYNH","schema_version":"1.0","canonical_sha256":"e36e1c61a78cef766c5848cbb05d033c16882d2737e9da41828244dc87e0b77e","source":{"kind":"arxiv","id":"2311.17296","version":2},"attestation_state":"computed","paper":{"title":"Mirror Duality in Convex Optimization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Asuman Ozdaglar, Chanwoo Park, Ernest K. Ryu, Jaeyeon Kim, Jelena Diakonikolas","submitted_at":"2023-11-29T00:48:18Z","abstract_excerpt":"While first-order optimization methods are usually designed to efficiently reduce the function value $f(x)$, there has been recent interest in methods efficiently reducing the magnitude of $\\nabla f(x)$, and the findings show that the two types of methods exhibit a certain symmetry. In this work, we present mirror duality, a one-to-one correspondence between mirror-descent-type methods reducing function value and reducing gradient magnitude. Using mirror duality, we obtain the dual accelerated mirror descent (dual-AMD) method that efficiently reduces $\\psi^*(\\nabla f(x))$, where $\\psi$ is a di"},"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":"2311.17296","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"math.OC","submitted_at":"2023-11-29T00:48:18Z","cross_cats_sorted":[],"title_canon_sha256":"89e39cfbe7a07dfe3337e279f78f77cd6c6190774651ac716716fb6d66d40e24","abstract_canon_sha256":"273d208f6920a28a4ef32df1e4b7e57017f2f0253fc3cf40ad76a5531485dc0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:21.111574Z","signature_b64":"4E7+OS2y/7L6b9C1RF/fi5LSf0AaIXTGtIjZuHnjReMAOvGc4iG1cqpHG0fc3zkDDaQw8ABnq4GMqLre2ixZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e36e1c61a78cef766c5848cbb05d033c16882d2737e9da41828244dc87e0b77e","last_reissued_at":"2026-07-05T08:19:21.111072Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:21.111072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mirror Duality in Convex Optimization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Asuman Ozdaglar, Chanwoo Park, Ernest K. Ryu, Jaeyeon Kim, Jelena Diakonikolas","submitted_at":"2023-11-29T00:48:18Z","abstract_excerpt":"While first-order optimization methods are usually designed to efficiently reduce the function value $f(x)$, there has been recent interest in methods efficiently reducing the magnitude of $\\nabla f(x)$, and the findings show that the two types of methods exhibit a certain symmetry. In this work, we present mirror duality, a one-to-one correspondence between mirror-descent-type methods reducing function value and reducing gradient magnitude. Using mirror duality, we obtain the dual accelerated mirror descent (dual-AMD) method that efficiently reduces $\\psi^*(\\nabla f(x))$, where $\\psi$ is a di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17296","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/2311.17296/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":"2311.17296","created_at":"2026-07-05T08:19:21.111135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17296v2","created_at":"2026-07-05T08:19:21.111135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17296","created_at":"2026-07-05T08:19:21.111135+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NXBYYNHRTXX","created_at":"2026-07-05T08:19:21.111135+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NXBYYNHRTXXM3CY","created_at":"2026-07-05T08:19:21.111135+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NXBYYNH","created_at":"2026-07-05T08:19:21.111135+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00665","citing_title":"Effective dynamics of the Sinkhorn algorithm in the regime of low entropy regularization","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02787","citing_title":"Adaptive Accelerated Mirror Descent in Primal and Dual Spaces","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28973","citing_title":"Sharp $O(1/k)$ convergence rate for the Sinkhorn algorithm via a local analysis","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20370","citing_title":"Nonlinearly preconditioned gradient flows","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02231","citing_title":"A Theory of Composition and Duality of Extremal Optimal Fixed-Point Algorithms","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4NXBYYNHRTXXM3CYJDF3AXIDHQ","json":"https://pith.science/pith/4NXBYYNHRTXXM3CYJDF3AXIDHQ.json","graph_json":"https://pith.science/api/pith-number/4NXBYYNHRTXXM3CYJDF3AXIDHQ/graph.json","events_json":"https://pith.science/api/pith-number/4NXBYYNHRTXXM3CYJDF3AXIDHQ/events.json","paper":"https://pith.science/paper/4NXBYYNH"},"agent_actions":{"view_html":"https://pith.science/pith/4NXBYYNHRTXXM3CYJDF3AXIDHQ","download_json":"https://pith.science/pith/4NXBYYNHRTXXM3CYJDF3AXIDHQ.json","view_paper":"https://pith.science/paper/4NXBYYNH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17296&json=true","fetch_graph":"https://pith.science/api/pith-number/4NXBYYNHRTXXM3CYJDF3AXIDHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4NXBYYNHRTXXM3CYJDF3AXIDHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NXBYYNHRTXXM3CYJDF3AXIDHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NXBYYNHRTXXM3CYJDF3AXIDHQ/action/storage_attestation","attest_author":"https://pith.science/pith/4NXBYYNHRTXXM3CYJDF3AXIDHQ/action/author_attestation","sign_citation":"https://pith.science/pith/4NXBYYNHRTXXM3CYJDF3AXIDHQ/action/citation_signature","submit_replication":"https://pith.science/pith/4NXBYYNHRTXXM3CYJDF3AXIDHQ/action/replication_record"}},"created_at":"2026-07-05T08:19:21.111135+00:00","updated_at":"2026-07-05T08:19:21.111135+00:00"}