{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BIPAZBEK3XUPOTVUJZXVTOC6CG","short_pith_number":"pith:BIPAZBEK","schema_version":"1.0","canonical_sha256":"0a1e0c848adde8f74eb44e6f59b85e11bc54261252ebca275754f87dde891257","source":{"kind":"arxiv","id":"2506.13984","version":1},"attestation_state":"computed","paper":{"title":"Mirror Descent Using the Tempesta Generalized Multi-parametric Logarithms","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrzej Cichocki","submitted_at":"2025-06-08T17:48:44Z","abstract_excerpt":"In this paper, we develop a wide class Mirror Descent (MD) algorithms, which play a key role in machine learning. For this purpose we formulated the constrained optimization problem, in which we exploits the Bregman divergence with the Tempesta multi-parametric deformation logarithm as a link function. This link function called also mirror function defines the mapping between the primal and dual spaces and is associated with a very-wide (in fact, theoretically infinite) class of generalized trace-form entropies. In order to derive novel MD updates, we estimate generalized exponential function,"},"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":"2506.13984","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-08T17:48:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3f394795b55ead1aef4922baf73aa8de016ac5aceb9303664b37bae66bfe79f2","abstract_canon_sha256":"fbd30f412eb7c1c62310e68578dc10bd1cdccd474358829c35a99cf7d0d9e9d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:46.784072Z","signature_b64":"4PwY3u4sYHGIL9k3H4/RykAduNcZkHltrwJ/el5KP/bOLREdbcCITndFVEOLYh/jjX0VTNjTZufbuyEzCnmcDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a1e0c848adde8f74eb44e6f59b85e11bc54261252ebca275754f87dde891257","last_reissued_at":"2026-07-05T11:22:46.783591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:46.783591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mirror Descent Using the Tempesta Generalized Multi-parametric Logarithms","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrzej Cichocki","submitted_at":"2025-06-08T17:48:44Z","abstract_excerpt":"In this paper, we develop a wide class Mirror Descent (MD) algorithms, which play a key role in machine learning. For this purpose we formulated the constrained optimization problem, in which we exploits the Bregman divergence with the Tempesta multi-parametric deformation logarithm as a link function. This link function called also mirror function defines the mapping between the primal and dual spaces and is associated with a very-wide (in fact, theoretically infinite) class of generalized trace-form entropies. In order to derive novel MD updates, we estimate generalized exponential function,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13984","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.13984/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":"2506.13984","created_at":"2026-07-05T11:22:46.783654+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13984v1","created_at":"2026-07-05T11:22:46.783654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13984","created_at":"2026-07-05T11:22:46.783654+00:00"},{"alias_kind":"pith_short_12","alias_value":"BIPAZBEK3XUP","created_at":"2026-07-05T11:22:46.783654+00:00"},{"alias_kind":"pith_short_16","alias_value":"BIPAZBEK3XUPOTVU","created_at":"2026-07-05T11:22:46.783654+00:00"},{"alias_kind":"pith_short_8","alias_value":"BIPAZBEK","created_at":"2026-07-05T11:22:46.783654+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.17500","citing_title":"Generalized Euler Logarithm and its Applications in Machine Learning: Natural Gradient, Backpropagation, Generalized EG, Mirror Descent and OLPS","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BIPAZBEK3XUPOTVUJZXVTOC6CG","json":"https://pith.science/pith/BIPAZBEK3XUPOTVUJZXVTOC6CG.json","graph_json":"https://pith.science/api/pith-number/BIPAZBEK3XUPOTVUJZXVTOC6CG/graph.json","events_json":"https://pith.science/api/pith-number/BIPAZBEK3XUPOTVUJZXVTOC6CG/events.json","paper":"https://pith.science/paper/BIPAZBEK"},"agent_actions":{"view_html":"https://pith.science/pith/BIPAZBEK3XUPOTVUJZXVTOC6CG","download_json":"https://pith.science/pith/BIPAZBEK3XUPOTVUJZXVTOC6CG.json","view_paper":"https://pith.science/paper/BIPAZBEK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13984&json=true","fetch_graph":"https://pith.science/api/pith-number/BIPAZBEK3XUPOTVUJZXVTOC6CG/graph.json","fetch_events":"https://pith.science/api/pith-number/BIPAZBEK3XUPOTVUJZXVTOC6CG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BIPAZBEK3XUPOTVUJZXVTOC6CG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BIPAZBEK3XUPOTVUJZXVTOC6CG/action/storage_attestation","attest_author":"https://pith.science/pith/BIPAZBEK3XUPOTVUJZXVTOC6CG/action/author_attestation","sign_citation":"https://pith.science/pith/BIPAZBEK3XUPOTVUJZXVTOC6CG/action/citation_signature","submit_replication":"https://pith.science/pith/BIPAZBEK3XUPOTVUJZXVTOC6CG/action/replication_record"}},"created_at":"2026-07-05T11:22:46.783654+00:00","updated_at":"2026-07-05T11:22:46.783654+00:00"}