{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4TYNNRFEYCQ3QWN5PRZO4LTELW","short_pith_number":"pith:4TYNNRFE","schema_version":"1.0","canonical_sha256":"e4f0d6c4a4c0a1b859bd7c72ee2e645d86650f3378ca64b682ea3998f65f30dc","source":{"kind":"arxiv","id":"1910.12204","version":1},"attestation_state":"computed","paper":{"title":"Spectral Algorithm for Low-rank Multitask Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ami Wiesel, Avinatan Hassidim, Gal Elidan, Sella Nevo, Yossi Matias, Yotam Gigi","submitted_at":"2019-10-27T08:00:17Z","abstract_excerpt":"Multitask learning, i.e. taking advantage of the relatedness of individual tasks in order to improve performance on all of them, is a core challenge in the field of machine learning. We focus on matrix regression tasks where the rank of the weight matrix is constrained to reduce sample complexity. We introduce the common mechanism regression (CMR) model which assumes a shared left low-rank component across all tasks, but allows an individual per-task right low-rank component. This dramatically reduces the number of samples needed for accurate estimation. The problem of jointly recovering the c"},"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":"1910.12204","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-27T08:00:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d6aa5cbc386749154b296c42ed8f42f26926d1d1e724da10c7f049f6e8a8067d","abstract_canon_sha256":"d9f1e1461d9f208087cc3508adf0dfde461d6cc4a43eb7fbd1c6e756d0b648c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:14.041269Z","signature_b64":"87X/mDwNj4ttQ7zDjeYWYYG1LQHACAZNmZEjGgLQ6eF0AaK3piAfmFT8XyMC03pdvmARMHPMI02dHW2kC6ONCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4f0d6c4a4c0a1b859bd7c72ee2e645d86650f3378ca64b682ea3998f65f30dc","last_reissued_at":"2026-07-05T00:15:14.040936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:14.040936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectral Algorithm for Low-rank Multitask Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ami Wiesel, Avinatan Hassidim, Gal Elidan, Sella Nevo, Yossi Matias, Yotam Gigi","submitted_at":"2019-10-27T08:00:17Z","abstract_excerpt":"Multitask learning, i.e. taking advantage of the relatedness of individual tasks in order to improve performance on all of them, is a core challenge in the field of machine learning. We focus on matrix regression tasks where the rank of the weight matrix is constrained to reduce sample complexity. We introduce the common mechanism regression (CMR) model which assumes a shared left low-rank component across all tasks, but allows an individual per-task right low-rank component. This dramatically reduces the number of samples needed for accurate estimation. The problem of jointly recovering the c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.12204","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/1910.12204/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":"1910.12204","created_at":"2026-07-05T00:15:14.040990+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.12204v1","created_at":"2026-07-05T00:15:14.040990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.12204","created_at":"2026-07-05T00:15:14.040990+00:00"},{"alias_kind":"pith_short_12","alias_value":"4TYNNRFEYCQ3","created_at":"2026-07-05T00:15:14.040990+00:00"},{"alias_kind":"pith_short_16","alias_value":"4TYNNRFEYCQ3QWN5","created_at":"2026-07-05T00:15:14.040990+00:00"},{"alias_kind":"pith_short_8","alias_value":"4TYNNRFE","created_at":"2026-07-05T00:15:14.040990+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/4TYNNRFEYCQ3QWN5PRZO4LTELW","json":"https://pith.science/pith/4TYNNRFEYCQ3QWN5PRZO4LTELW.json","graph_json":"https://pith.science/api/pith-number/4TYNNRFEYCQ3QWN5PRZO4LTELW/graph.json","events_json":"https://pith.science/api/pith-number/4TYNNRFEYCQ3QWN5PRZO4LTELW/events.json","paper":"https://pith.science/paper/4TYNNRFE"},"agent_actions":{"view_html":"https://pith.science/pith/4TYNNRFEYCQ3QWN5PRZO4LTELW","download_json":"https://pith.science/pith/4TYNNRFEYCQ3QWN5PRZO4LTELW.json","view_paper":"https://pith.science/paper/4TYNNRFE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.12204&json=true","fetch_graph":"https://pith.science/api/pith-number/4TYNNRFEYCQ3QWN5PRZO4LTELW/graph.json","fetch_events":"https://pith.science/api/pith-number/4TYNNRFEYCQ3QWN5PRZO4LTELW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4TYNNRFEYCQ3QWN5PRZO4LTELW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4TYNNRFEYCQ3QWN5PRZO4LTELW/action/storage_attestation","attest_author":"https://pith.science/pith/4TYNNRFEYCQ3QWN5PRZO4LTELW/action/author_attestation","sign_citation":"https://pith.science/pith/4TYNNRFEYCQ3QWN5PRZO4LTELW/action/citation_signature","submit_replication":"https://pith.science/pith/4TYNNRFEYCQ3QWN5PRZO4LTELW/action/replication_record"}},"created_at":"2026-07-05T00:15:14.040990+00:00","updated_at":"2026-07-05T00:15:14.040990+00:00"}