{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:EZ54T4JBCPUW4JZMJO7PDC52XI","short_pith_number":"pith:EZ54T4JB","schema_version":"1.0","canonical_sha256":"267bc9f12113e96e272c4bbef18bbaba0077707ade2de8ebea2fda756437b5a1","source":{"kind":"arxiv","id":"1606.02206","version":5},"attestation_state":"computed","paper":{"title":"A Minimax Approach to Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"David Tse, Farzan Farnia","submitted_at":"2016-06-07T16:39:09Z","abstract_excerpt":"Given a task of predicting $Y$ from $X$, a loss function $L$, and a set of probability distributions $\\Gamma$ on $(X,Y)$, what is the optimal decision rule minimizing the worst-case expected loss over $\\Gamma$? In this paper, we address this question by introducing a generalization of the principle of maximum entropy. Applying this principle to sets of distributions with marginal on $X$ constrained to be the empirical marginal from the data, we develop a general minimax approach for supervised learning problems. While for some loss functions such as squared-error and log loss, the minimax appr"},"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":"1606.02206","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-07T16:39:09Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"title_canon_sha256":"8d6c0241a871fe027138be53a1b3b674b1ff7686a698547a42f199895e9e4484","abstract_canon_sha256":"62a82e2ae966640562f75f70ed7ae3c1e999cf3eb0eecc587bbb23b931ed59a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:01.958815Z","signature_b64":"wmBuVW29L3v2afPBHjsXiTRws9CKDGhiZbFIRRqFNSMY+xhDiFdmnvTazMUEmsPnUVEpdQ/6yJbDJ2UJN3P0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"267bc9f12113e96e272c4bbef18bbaba0077707ade2de8ebea2fda756437b5a1","last_reissued_at":"2026-05-18T00:41:01.958337Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:01.958337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Minimax Approach to Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"David Tse, Farzan Farnia","submitted_at":"2016-06-07T16:39:09Z","abstract_excerpt":"Given a task of predicting $Y$ from $X$, a loss function $L$, and a set of probability distributions $\\Gamma$ on $(X,Y)$, what is the optimal decision rule minimizing the worst-case expected loss over $\\Gamma$? In this paper, we address this question by introducing a generalization of the principle of maximum entropy. Applying this principle to sets of distributions with marginal on $X$ constrained to be the empirical marginal from the data, we develop a general minimax approach for supervised learning problems. While for some loss functions such as squared-error and log loss, the minimax appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.02206","kind":"arxiv","version":5},"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":"1606.02206","created_at":"2026-05-18T00:41:01.958416+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.02206v5","created_at":"2026-05-18T00:41:01.958416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.02206","created_at":"2026-05-18T00:41:01.958416+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZ54T4JBCPUW","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZ54T4JBCPUW4JZM","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZ54T4JB","created_at":"2026-05-18T12:30:15.759754+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/EZ54T4JBCPUW4JZMJO7PDC52XI","json":"https://pith.science/pith/EZ54T4JBCPUW4JZMJO7PDC52XI.json","graph_json":"https://pith.science/api/pith-number/EZ54T4JBCPUW4JZMJO7PDC52XI/graph.json","events_json":"https://pith.science/api/pith-number/EZ54T4JBCPUW4JZMJO7PDC52XI/events.json","paper":"https://pith.science/paper/EZ54T4JB"},"agent_actions":{"view_html":"https://pith.science/pith/EZ54T4JBCPUW4JZMJO7PDC52XI","download_json":"https://pith.science/pith/EZ54T4JBCPUW4JZMJO7PDC52XI.json","view_paper":"https://pith.science/paper/EZ54T4JB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.02206&json=true","fetch_graph":"https://pith.science/api/pith-number/EZ54T4JBCPUW4JZMJO7PDC52XI/graph.json","fetch_events":"https://pith.science/api/pith-number/EZ54T4JBCPUW4JZMJO7PDC52XI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZ54T4JBCPUW4JZMJO7PDC52XI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZ54T4JBCPUW4JZMJO7PDC52XI/action/storage_attestation","attest_author":"https://pith.science/pith/EZ54T4JBCPUW4JZMJO7PDC52XI/action/author_attestation","sign_citation":"https://pith.science/pith/EZ54T4JBCPUW4JZMJO7PDC52XI/action/citation_signature","submit_replication":"https://pith.science/pith/EZ54T4JBCPUW4JZMJO7PDC52XI/action/replication_record"}},"created_at":"2026-05-18T00:41:01.958416+00:00","updated_at":"2026-05-18T00:41:01.958416+00:00"}