{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VLAI55DMFYLQQ3VIYKUDNOQME4","short_pith_number":"pith:VLAI55DM","schema_version":"1.0","canonical_sha256":"aac08ef46c2e17086ea8c2a836ba0c27100d5023157863165855169c0f023ad3","source":{"kind":"arxiv","id":"1906.02717","version":3},"attestation_state":"computed","paper":{"title":"Adaptive Gradient-Based Meta-Learning Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ameet Talwalkar, Maria-Florina Balcan, Mikhail Khodak","submitted_at":"2019-06-06T17:36:34Z","abstract_excerpt":"We build a theoretical framework for designing and understanding practical meta-learning methods that integrates sophisticated formalizations of task-similarity with the extensive literature on online convex optimization and sequential prediction algorithms. Our approach enables the task-similarity to be learned adaptively, provides sharper transfer-risk bounds in the setting of statistical learning-to-learn, and leads to straightforward derivations of average-case regret bounds for efficient algorithms in settings where the task-environment changes dynamically or the tasks share a certain geo"},"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":"1906.02717","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-06T17:36:34Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"2096b40f30ca2763b6e34358ce6415555132370fff66add17fed667e9be1cdf1","abstract_canon_sha256":"d84360e1f9a8569134662ed08f1b3e10ce00c4c6a78585ea268cdb574897081f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:38.757899Z","signature_b64":"LwJFw6DQXxhtxE0uWbUuUfnt27Su7MZOyTYAMFjAXPxR9rGib+33xkHhusSkNIco7NG+8UGLHimczygZkaDBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aac08ef46c2e17086ea8c2a836ba0c27100d5023157863165855169c0f023ad3","last_reissued_at":"2026-07-05T00:24:38.757544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:38.757544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Gradient-Based Meta-Learning Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ameet Talwalkar, Maria-Florina Balcan, Mikhail Khodak","submitted_at":"2019-06-06T17:36:34Z","abstract_excerpt":"We build a theoretical framework for designing and understanding practical meta-learning methods that integrates sophisticated formalizations of task-similarity with the extensive literature on online convex optimization and sequential prediction algorithms. Our approach enables the task-similarity to be learned adaptively, provides sharper transfer-risk bounds in the setting of statistical learning-to-learn, and leads to straightforward derivations of average-case regret bounds for efficient algorithms in settings where the task-environment changes dynamically or the tasks share a certain geo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02717","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/1906.02717/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":"1906.02717","created_at":"2026-07-05T00:24:38.757607+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.02717v3","created_at":"2026-07-05T00:24:38.757607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02717","created_at":"2026-07-05T00:24:38.757607+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLAI55DMFYLQ","created_at":"2026-07-05T00:24:38.757607+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLAI55DMFYLQQ3VI","created_at":"2026-07-05T00:24:38.757607+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLAI55DM","created_at":"2026-07-05T00:24:38.757607+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.07873","citing_title":"Federated Learning: Challenges, Methods, and Future Directions","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLAI55DMFYLQQ3VIYKUDNOQME4","json":"https://pith.science/pith/VLAI55DMFYLQQ3VIYKUDNOQME4.json","graph_json":"https://pith.science/api/pith-number/VLAI55DMFYLQQ3VIYKUDNOQME4/graph.json","events_json":"https://pith.science/api/pith-number/VLAI55DMFYLQQ3VIYKUDNOQME4/events.json","paper":"https://pith.science/paper/VLAI55DM"},"agent_actions":{"view_html":"https://pith.science/pith/VLAI55DMFYLQQ3VIYKUDNOQME4","download_json":"https://pith.science/pith/VLAI55DMFYLQQ3VIYKUDNOQME4.json","view_paper":"https://pith.science/paper/VLAI55DM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.02717&json=true","fetch_graph":"https://pith.science/api/pith-number/VLAI55DMFYLQQ3VIYKUDNOQME4/graph.json","fetch_events":"https://pith.science/api/pith-number/VLAI55DMFYLQQ3VIYKUDNOQME4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLAI55DMFYLQQ3VIYKUDNOQME4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLAI55DMFYLQQ3VIYKUDNOQME4/action/storage_attestation","attest_author":"https://pith.science/pith/VLAI55DMFYLQQ3VIYKUDNOQME4/action/author_attestation","sign_citation":"https://pith.science/pith/VLAI55DMFYLQQ3VIYKUDNOQME4/action/citation_signature","submit_replication":"https://pith.science/pith/VLAI55DMFYLQQ3VIYKUDNOQME4/action/replication_record"}},"created_at":"2026-07-05T00:24:38.757607+00:00","updated_at":"2026-07-05T00:24:38.757607+00:00"}