{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LB247RW4XX6O4X2QSRUGQJCODT","short_pith_number":"pith:LB247RW4","schema_version":"1.0","canonical_sha256":"5875cfc6dcbdfcee5f50946868244e1cc731414608642b4057e3149f0df61cab","source":{"kind":"arxiv","id":"1903.10399","version":1},"attestation_state":"computed","paper":{"title":"Learning-to-Learn Stochastic Gradient Descent with Biased Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Carlo Ciliberto, Giulia Denevi, Massimiliano Pontil, Riccardo Grazzi","submitted_at":"2019-03-25T15:26:56Z","abstract_excerpt":"We study the problem of learning-to-learn: inferring a learning algorithm that works well on tasks sampled from an unknown distribution. As class of algorithms we consider Stochastic Gradient Descent on the true risk regularized by the square euclidean distance to a bias vector. We present an average excess risk bound for such a learning algorithm. This result quantifies the potential benefit of using a bias vector with respect to the unbiased case. We then address the problem of estimating the bias from a sequence of tasks. We propose a meta-algorithm which incrementally updates the bias, as "},"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":"1903.10399","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-25T15:26:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dd4b268f20ad9b9b2598338e9a251c4cc7e726b687146f01ad3dda8ac187f7bf","abstract_canon_sha256":"057b630e6cad76f1f40729178dcf8d2dd28152fa05aa37dc7a9b7e2937e7b761"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:29.542830Z","signature_b64":"buWMnwgey9l9/6f6rvRTr0YtJ+udOl132TxrLC56fs9DlwNH5jxjM6gMvbySeO/4FiEEO8v29hjRZ7YE6CW9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5875cfc6dcbdfcee5f50946868244e1cc731414608642b4057e3149f0df61cab","last_reissued_at":"2026-05-17T23:50:29.542196Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:29.542196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning-to-Learn Stochastic Gradient Descent with Biased Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Carlo Ciliberto, Giulia Denevi, Massimiliano Pontil, Riccardo Grazzi","submitted_at":"2019-03-25T15:26:56Z","abstract_excerpt":"We study the problem of learning-to-learn: inferring a learning algorithm that works well on tasks sampled from an unknown distribution. As class of algorithms we consider Stochastic Gradient Descent on the true risk regularized by the square euclidean distance to a bias vector. We present an average excess risk bound for such a learning algorithm. This result quantifies the potential benefit of using a bias vector with respect to the unbiased case. We then address the problem of estimating the bias from a sequence of tasks. We propose a meta-algorithm which incrementally updates the bias, as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10399","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":""},"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":"1903.10399","created_at":"2026-05-17T23:50:29.542307+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.10399v1","created_at":"2026-05-17T23:50:29.542307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10399","created_at":"2026-05-17T23:50:29.542307+00:00"},{"alias_kind":"pith_short_12","alias_value":"LB247RW4XX6O","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"LB247RW4XX6O4X2Q","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"LB247RW4","created_at":"2026-05-18T12:33:21.387695+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/LB247RW4XX6O4X2QSRUGQJCODT","json":"https://pith.science/pith/LB247RW4XX6O4X2QSRUGQJCODT.json","graph_json":"https://pith.science/api/pith-number/LB247RW4XX6O4X2QSRUGQJCODT/graph.json","events_json":"https://pith.science/api/pith-number/LB247RW4XX6O4X2QSRUGQJCODT/events.json","paper":"https://pith.science/paper/LB247RW4"},"agent_actions":{"view_html":"https://pith.science/pith/LB247RW4XX6O4X2QSRUGQJCODT","download_json":"https://pith.science/pith/LB247RW4XX6O4X2QSRUGQJCODT.json","view_paper":"https://pith.science/paper/LB247RW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.10399&json=true","fetch_graph":"https://pith.science/api/pith-number/LB247RW4XX6O4X2QSRUGQJCODT/graph.json","fetch_events":"https://pith.science/api/pith-number/LB247RW4XX6O4X2QSRUGQJCODT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LB247RW4XX6O4X2QSRUGQJCODT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LB247RW4XX6O4X2QSRUGQJCODT/action/storage_attestation","attest_author":"https://pith.science/pith/LB247RW4XX6O4X2QSRUGQJCODT/action/author_attestation","sign_citation":"https://pith.science/pith/LB247RW4XX6O4X2QSRUGQJCODT/action/citation_signature","submit_replication":"https://pith.science/pith/LB247RW4XX6O4X2QSRUGQJCODT/action/replication_record"}},"created_at":"2026-05-17T23:50:29.542307+00:00","updated_at":"2026-05-17T23:50:29.542307+00:00"}