{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EXJV2A4U3VQVPVVPJNLL7K6KVD","short_pith_number":"pith:EXJV2A4U","schema_version":"1.0","canonical_sha256":"25d35d0394dd6157d6af4b56bfabcaa8ff8431491919f6c1058964b3c98fd36e","source":{"kind":"arxiv","id":"2202.07537","version":2},"attestation_state":"computed","paper":{"title":"Information-Theoretic Analysis of Minimax Excess Risk","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Behrad Moniri, Hassan Hafez-Kolahi, Shohreh Kasaei","submitted_at":"2022-02-15T16:13:40Z","abstract_excerpt":"Two main concepts studied in machine learning theory are generalization gap (difference between train and test error) and excess risk (difference between test error and the minimum possible error). While information-theoretic tools have been used extensively to study the generalization gap of learning algorithms, the information-theoretic nature of excess risk has not yet been fully investigated. In this paper, some steps are taken toward this goal. We consider the frequentist problem of minimax excess risk as a zero-sum game between the algorithm designer and the world. Then, we argue that it"},"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":"2202.07537","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-15T16:13:40Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"57f1bc42758d7efe26cd37cb6a17426fa8961cd850be98b88110628970133ba4","abstract_canon_sha256":"fe1351405dac0fdb7160cd6bec5405998b0797ece2be88ad0cc72b923fc003c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:46:12.882893Z","signature_b64":"r3QEriFiMFLk79D9ZmhYy+qEEmazsbXBduYUo/HkUJlxV9dagZaT8lnemxE31+alEwiQxta7k6YQWH6wB3YgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25d35d0394dd6157d6af4b56bfabcaa8ff8431491919f6c1058964b3c98fd36e","last_reissued_at":"2026-07-05T05:46:12.882349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:46:12.882349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Information-Theoretic Analysis of Minimax Excess Risk","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Behrad Moniri, Hassan Hafez-Kolahi, Shohreh Kasaei","submitted_at":"2022-02-15T16:13:40Z","abstract_excerpt":"Two main concepts studied in machine learning theory are generalization gap (difference between train and test error) and excess risk (difference between test error and the minimum possible error). While information-theoretic tools have been used extensively to study the generalization gap of learning algorithms, the information-theoretic nature of excess risk has not yet been fully investigated. In this paper, some steps are taken toward this goal. We consider the frequentist problem of minimax excess risk as a zero-sum game between the algorithm designer and the world. Then, we argue that it"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07537","kind":"arxiv","version":2},"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/2202.07537/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":"2202.07537","created_at":"2026-07-05T05:46:12.882411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.07537v2","created_at":"2026-07-05T05:46:12.882411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07537","created_at":"2026-07-05T05:46:12.882411+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXJV2A4U3VQV","created_at":"2026-07-05T05:46:12.882411+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXJV2A4U3VQVPVVP","created_at":"2026-07-05T05:46:12.882411+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXJV2A4U","created_at":"2026-07-05T05:46:12.882411+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/EXJV2A4U3VQVPVVPJNLL7K6KVD","json":"https://pith.science/pith/EXJV2A4U3VQVPVVPJNLL7K6KVD.json","graph_json":"https://pith.science/api/pith-number/EXJV2A4U3VQVPVVPJNLL7K6KVD/graph.json","events_json":"https://pith.science/api/pith-number/EXJV2A4U3VQVPVVPJNLL7K6KVD/events.json","paper":"https://pith.science/paper/EXJV2A4U"},"agent_actions":{"view_html":"https://pith.science/pith/EXJV2A4U3VQVPVVPJNLL7K6KVD","download_json":"https://pith.science/pith/EXJV2A4U3VQVPVVPJNLL7K6KVD.json","view_paper":"https://pith.science/paper/EXJV2A4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.07537&json=true","fetch_graph":"https://pith.science/api/pith-number/EXJV2A4U3VQVPVVPJNLL7K6KVD/graph.json","fetch_events":"https://pith.science/api/pith-number/EXJV2A4U3VQVPVVPJNLL7K6KVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXJV2A4U3VQVPVVPJNLL7K6KVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXJV2A4U3VQVPVVPJNLL7K6KVD/action/storage_attestation","attest_author":"https://pith.science/pith/EXJV2A4U3VQVPVVPJNLL7K6KVD/action/author_attestation","sign_citation":"https://pith.science/pith/EXJV2A4U3VQVPVVPJNLL7K6KVD/action/citation_signature","submit_replication":"https://pith.science/pith/EXJV2A4U3VQVPVVPJNLL7K6KVD/action/replication_record"}},"created_at":"2026-07-05T05:46:12.882411+00:00","updated_at":"2026-07-05T05:46:12.882411+00:00"}