{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GLQV7WK4IELO3MG7JHNYU7FQSO","short_pith_number":"pith:GLQV7WK4","schema_version":"1.0","canonical_sha256":"32e15fd95c4116edb0df49db8a7cb093acaf9a7aff3fb9cf3231086e80de1d92","source":{"kind":"arxiv","id":"2412.04274","version":1},"attestation_state":"computed","paper":{"title":"Complexity of Vector-valued Prediction: From Linear Models to Stochastic Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Matan Schliserman, Tomer Koren","submitted_at":"2024-12-05T15:56:54Z","abstract_excerpt":"We study the problem of learning vector-valued linear predictors: these are prediction rules parameterized by a matrix that maps an $m$-dimensional feature vector to a $k$-dimensional target. We focus on the fundamental case with a convex and Lipschitz loss function, and show several new theoretical results that shed light on the complexity of this problem and its connection to related learning models. First, we give a tight characterization of the sample complexity of Empirical Risk Minimization (ERM) in this setting, establishing that $\\smash{\\widetilde{\\Omega}}(k/\\epsilon^2)$ examples are n"},"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":"2412.04274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T15:56:54Z","cross_cats_sorted":[],"title_canon_sha256":"7c59dba1770fa96648523f81284cc0721d8e8bf917f61d60b80b5122e780ff54","abstract_canon_sha256":"efbec89c31cf7d10fc19fe277403ade3372047b524edc1d89e6cc6ca9367d8f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:01.842557Z","signature_b64":"AIJwAVLelwZJMdCk/UVfbNT7RgdlkFx6RbBXw6QB1JkEchzciFl70tzBTlouUCjF7HZgSVGLdmcbs4dV74zDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32e15fd95c4116edb0df49db8a7cb093acaf9a7aff3fb9cf3231086e80de1d92","last_reissued_at":"2026-07-05T09:45:01.842092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:01.842092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Complexity of Vector-valued Prediction: From Linear Models to Stochastic Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Matan Schliserman, Tomer Koren","submitted_at":"2024-12-05T15:56:54Z","abstract_excerpt":"We study the problem of learning vector-valued linear predictors: these are prediction rules parameterized by a matrix that maps an $m$-dimensional feature vector to a $k$-dimensional target. We focus on the fundamental case with a convex and Lipschitz loss function, and show several new theoretical results that shed light on the complexity of this problem and its connection to related learning models. First, we give a tight characterization of the sample complexity of Empirical Risk Minimization (ERM) in this setting, establishing that $\\smash{\\widetilde{\\Omega}}(k/\\epsilon^2)$ examples are n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04274","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/2412.04274/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":"2412.04274","created_at":"2026-07-05T09:45:01.842145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04274v1","created_at":"2026-07-05T09:45:01.842145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04274","created_at":"2026-07-05T09:45:01.842145+00:00"},{"alias_kind":"pith_short_12","alias_value":"GLQV7WK4IELO","created_at":"2026-07-05T09:45:01.842145+00:00"},{"alias_kind":"pith_short_16","alias_value":"GLQV7WK4IELO3MG7","created_at":"2026-07-05T09:45:01.842145+00:00"},{"alias_kind":"pith_short_8","alias_value":"GLQV7WK4","created_at":"2026-07-05T09:45:01.842145+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22359","citing_title":"Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GLQV7WK4IELO3MG7JHNYU7FQSO","json":"https://pith.science/pith/GLQV7WK4IELO3MG7JHNYU7FQSO.json","graph_json":"https://pith.science/api/pith-number/GLQV7WK4IELO3MG7JHNYU7FQSO/graph.json","events_json":"https://pith.science/api/pith-number/GLQV7WK4IELO3MG7JHNYU7FQSO/events.json","paper":"https://pith.science/paper/GLQV7WK4"},"agent_actions":{"view_html":"https://pith.science/pith/GLQV7WK4IELO3MG7JHNYU7FQSO","download_json":"https://pith.science/pith/GLQV7WK4IELO3MG7JHNYU7FQSO.json","view_paper":"https://pith.science/paper/GLQV7WK4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04274&json=true","fetch_graph":"https://pith.science/api/pith-number/GLQV7WK4IELO3MG7JHNYU7FQSO/graph.json","fetch_events":"https://pith.science/api/pith-number/GLQV7WK4IELO3MG7JHNYU7FQSO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GLQV7WK4IELO3MG7JHNYU7FQSO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GLQV7WK4IELO3MG7JHNYU7FQSO/action/storage_attestation","attest_author":"https://pith.science/pith/GLQV7WK4IELO3MG7JHNYU7FQSO/action/author_attestation","sign_citation":"https://pith.science/pith/GLQV7WK4IELO3MG7JHNYU7FQSO/action/citation_signature","submit_replication":"https://pith.science/pith/GLQV7WK4IELO3MG7JHNYU7FQSO/action/replication_record"}},"created_at":"2026-07-05T09:45:01.842145+00:00","updated_at":"2026-07-05T09:45:01.842145+00:00"}