{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GYZU6DGC35WVEUBOVR57J6RMUS","short_pith_number":"pith:GYZU6DGC","schema_version":"1.0","canonical_sha256":"36334f0cc2df6d52502eac7bf4fa2ca4bebdc492ac488130f16c261ccff2f009","source":{"kind":"arxiv","id":"2009.01591","version":1},"attestation_state":"computed","paper":{"title":"Large Dimensional Analysis and Improvement of Multi Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hafiz Tiomoko, Malik Tiomoko, Romain Couillet","submitted_at":"2020-09-03T11:40:14Z","abstract_excerpt":"Multi Task Learning (MTL) efficiently leverages useful information contained in multiple related tasks to help improve the generalization performance of all tasks. This article conducts a large dimensional analysis of a simple but, as we shall see, extremely powerful when carefully tuned, Least Square Support Vector Machine (LSSVM) version of MTL, in the regime where the dimension $p$ of the data and their number $n$ grow large at the same rate.\n  Under mild assumptions on the input data, the theoretical analysis of the MTL-LSSVM algorithm first reveals the \"sufficient statistics\" exploited by"},"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":"2009.01591","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-09-03T11:40:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d3ff613e02c3103c3e58a87dfd44408730ba87ffbce282795a0ef3bf43eeaa23","abstract_canon_sha256":"738eb14bc09ca6bbd29769228c46307cdc5c024058836e08552671e313e82e00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:32:51.134169Z","signature_b64":"OlycMyf1GJYmdmvE1Vyck8cfIExojGMj1Yj5vtKL7yr+vX7HEIMv7j7Bc/C+8MtwS8vlFda5qkkGB5vP2SWlBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36334f0cc2df6d52502eac7bf4fa2ca4bebdc492ac488130f16c261ccff2f009","last_reissued_at":"2026-07-05T01:32:51.133751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:32:51.133751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Dimensional Analysis and Improvement of Multi Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hafiz Tiomoko, Malik Tiomoko, Romain Couillet","submitted_at":"2020-09-03T11:40:14Z","abstract_excerpt":"Multi Task Learning (MTL) efficiently leverages useful information contained in multiple related tasks to help improve the generalization performance of all tasks. This article conducts a large dimensional analysis of a simple but, as we shall see, extremely powerful when carefully tuned, Least Square Support Vector Machine (LSSVM) version of MTL, in the regime where the dimension $p$ of the data and their number $n$ grow large at the same rate.\n  Under mild assumptions on the input data, the theoretical analysis of the MTL-LSSVM algorithm first reveals the \"sufficient statistics\" exploited by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.01591","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/2009.01591/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":"2009.01591","created_at":"2026-07-05T01:32:51.133814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.01591v1","created_at":"2026-07-05T01:32:51.133814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.01591","created_at":"2026-07-05T01:32:51.133814+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYZU6DGC35WV","created_at":"2026-07-05T01:32:51.133814+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYZU6DGC35WVEUBO","created_at":"2026-07-05T01:32:51.133814+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYZU6DGC","created_at":"2026-07-05T01:32:51.133814+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15688","citing_title":"$\\alpha$-TCAV: A Unified Framework for Testing with Concept Activation Vectors","ref_index":103,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYZU6DGC35WVEUBOVR57J6RMUS","json":"https://pith.science/pith/GYZU6DGC35WVEUBOVR57J6RMUS.json","graph_json":"https://pith.science/api/pith-number/GYZU6DGC35WVEUBOVR57J6RMUS/graph.json","events_json":"https://pith.science/api/pith-number/GYZU6DGC35WVEUBOVR57J6RMUS/events.json","paper":"https://pith.science/paper/GYZU6DGC"},"agent_actions":{"view_html":"https://pith.science/pith/GYZU6DGC35WVEUBOVR57J6RMUS","download_json":"https://pith.science/pith/GYZU6DGC35WVEUBOVR57J6RMUS.json","view_paper":"https://pith.science/paper/GYZU6DGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.01591&json=true","fetch_graph":"https://pith.science/api/pith-number/GYZU6DGC35WVEUBOVR57J6RMUS/graph.json","fetch_events":"https://pith.science/api/pith-number/GYZU6DGC35WVEUBOVR57J6RMUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYZU6DGC35WVEUBOVR57J6RMUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYZU6DGC35WVEUBOVR57J6RMUS/action/storage_attestation","attest_author":"https://pith.science/pith/GYZU6DGC35WVEUBOVR57J6RMUS/action/author_attestation","sign_citation":"https://pith.science/pith/GYZU6DGC35WVEUBOVR57J6RMUS/action/citation_signature","submit_replication":"https://pith.science/pith/GYZU6DGC35WVEUBOVR57J6RMUS/action/replication_record"}},"created_at":"2026-07-05T01:32:51.133814+00:00","updated_at":"2026-07-05T01:32:51.133814+00:00"}