{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J6KCA72F7OX47P5VPEKR2Q6LRM","short_pith_number":"pith:J6KCA72F","schema_version":"1.0","canonical_sha256":"4f94207f45fbafcfbfb579151d43cb8b13566aa892abd1149f5953679d5893ec","source":{"kind":"arxiv","id":"2401.08893","version":3},"attestation_state":"computed","paper":{"title":"MADA: Meta-Adaptive Optimizers through hyper-gradient Descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Branislav Kveton, Can Karakus, Kaan Ozkara, Mingyi Hong, Parameswaran Raman, Shoham Sabach, Volkan Cevher","submitted_at":"2024-01-17T00:16:46Z","abstract_excerpt":"Following the introduction of Adam, several novel adaptive optimizers for deep learning have been proposed. These optimizers typically excel in some tasks but may not outperform Adam uniformly across all tasks. In this work, we introduce Meta-Adaptive Optimizers (MADA), a unified optimizer framework that can generalize several known optimizers and dynamically learn the most suitable one during training. The key idea in MADA is to parameterize the space of optimizers and dynamically search through it using hyper-gradient descent during training. We empirically compare MADA to other popular opti"},"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":"2401.08893","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-17T00:16:46Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"2f24a28856b951c45d949c7234a870a3152ac8caf96beaf9af9873e06121db1a","abstract_canon_sha256":"d1f10b52f691a722b34818232bc3a08fa217c18c9a1424b4cc05afdcb59893a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:35.018092Z","signature_b64":"aT3dGWwCCDzoHJYnSTj1ywM7xqeyoj6aJ7hl+t4JrfmvdpBrJ1A022KSR+WQc6E6589yD+b3XHhtc18C0LLODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f94207f45fbafcfbfb579151d43cb8b13566aa892abd1149f5953679d5893ec","last_reissued_at":"2026-07-05T08:32:35.017621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:35.017621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MADA: Meta-Adaptive Optimizers through hyper-gradient Descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Branislav Kveton, Can Karakus, Kaan Ozkara, Mingyi Hong, Parameswaran Raman, Shoham Sabach, Volkan Cevher","submitted_at":"2024-01-17T00:16:46Z","abstract_excerpt":"Following the introduction of Adam, several novel adaptive optimizers for deep learning have been proposed. These optimizers typically excel in some tasks but may not outperform Adam uniformly across all tasks. In this work, we introduce Meta-Adaptive Optimizers (MADA), a unified optimizer framework that can generalize several known optimizers and dynamically learn the most suitable one during training. The key idea in MADA is to parameterize the space of optimizers and dynamically search through it using hyper-gradient descent during training. We empirically compare MADA to other popular opti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08893","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.08893/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":"2401.08893","created_at":"2026-07-05T08:32:35.017678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08893v3","created_at":"2026-07-05T08:32:35.017678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08893","created_at":"2026-07-05T08:32:35.017678+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6KCA72F7OX4","created_at":"2026-07-05T08:32:35.017678+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6KCA72F7OX47P5V","created_at":"2026-07-05T08:32:35.017678+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6KCA72F","created_at":"2026-07-05T08:32:35.017678+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/J6KCA72F7OX47P5VPEKR2Q6LRM","json":"https://pith.science/pith/J6KCA72F7OX47P5VPEKR2Q6LRM.json","graph_json":"https://pith.science/api/pith-number/J6KCA72F7OX47P5VPEKR2Q6LRM/graph.json","events_json":"https://pith.science/api/pith-number/J6KCA72F7OX47P5VPEKR2Q6LRM/events.json","paper":"https://pith.science/paper/J6KCA72F"},"agent_actions":{"view_html":"https://pith.science/pith/J6KCA72F7OX47P5VPEKR2Q6LRM","download_json":"https://pith.science/pith/J6KCA72F7OX47P5VPEKR2Q6LRM.json","view_paper":"https://pith.science/paper/J6KCA72F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08893&json=true","fetch_graph":"https://pith.science/api/pith-number/J6KCA72F7OX47P5VPEKR2Q6LRM/graph.json","fetch_events":"https://pith.science/api/pith-number/J6KCA72F7OX47P5VPEKR2Q6LRM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6KCA72F7OX47P5VPEKR2Q6LRM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6KCA72F7OX47P5VPEKR2Q6LRM/action/storage_attestation","attest_author":"https://pith.science/pith/J6KCA72F7OX47P5VPEKR2Q6LRM/action/author_attestation","sign_citation":"https://pith.science/pith/J6KCA72F7OX47P5VPEKR2Q6LRM/action/citation_signature","submit_replication":"https://pith.science/pith/J6KCA72F7OX47P5VPEKR2Q6LRM/action/replication_record"}},"created_at":"2026-07-05T08:32:35.017678+00:00","updated_at":"2026-07-05T08:32:35.017678+00:00"}