{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ZKYSYXG2KE4O7FHG35T3CRTCEI","short_pith_number":"pith:ZKYSYXG2","schema_version":"1.0","canonical_sha256":"cab12c5cda5138ef94e6df67b1466222124ae2dec00cfb8d57512ecf87129b32","source":{"kind":"arxiv","id":"1605.02268","version":2},"attestation_state":"computed","paper":{"title":"Rate-Distortion Bounds on Bayes Risk in Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.IT","stat.ML"],"primary_cat":"cs.IT","authors_text":"Ahmad Beirami, Matthew Nokleby, Robert Calderbank","submitted_at":"2016-05-08T03:54:34Z","abstract_excerpt":"We present an information-theoretic framework for bounding the number of labeled samples needed to train a classifier in a parametric Bayesian setting. We derive bounds on the average $L_p$ distance between the learned classifier and the true maximum a posteriori classifier, which are well-established surrogates for the excess classification error due to imperfect learning. We provide lower and upper bounds on the rate-distortion function, using $L_p$ loss as the distortion measure, of a maximum a priori classifier in terms of the differential entropy of the posterior distribution and a quanti"},"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":"1605.02268","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2016-05-08T03:54:34Z","cross_cats_sorted":["cs.LG","math.IT","stat.ML"],"title_canon_sha256":"386bc7f084d37786bcb769691995b0644ae6a46d53016f21d52b4c8475a2671d","abstract_canon_sha256":"62b9ae963591f3bca5550e68e747d2b61dfa606fcee5718af589edb6b293d90e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:22.638051Z","signature_b64":"SewNnQmF2gVIzoGNzzjU0FeYh+EqNpJSaqNveaodrArcD8oI42X70D88+XKoOMdfrgSvmQ0+ZJKYHzZjPVCLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cab12c5cda5138ef94e6df67b1466222124ae2dec00cfb8d57512ecf87129b32","last_reissued_at":"2026-05-18T00:30:22.637335Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:22.637335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rate-Distortion Bounds on Bayes Risk in Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.IT","stat.ML"],"primary_cat":"cs.IT","authors_text":"Ahmad Beirami, Matthew Nokleby, Robert Calderbank","submitted_at":"2016-05-08T03:54:34Z","abstract_excerpt":"We present an information-theoretic framework for bounding the number of labeled samples needed to train a classifier in a parametric Bayesian setting. We derive bounds on the average $L_p$ distance between the learned classifier and the true maximum a posteriori classifier, which are well-established surrogates for the excess classification error due to imperfect learning. We provide lower and upper bounds on the rate-distortion function, using $L_p$ loss as the distortion measure, of a maximum a priori classifier in terms of the differential entropy of the posterior distribution and a quanti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.02268","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":""},"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":"1605.02268","created_at":"2026-05-18T00:30:22.637439+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.02268v2","created_at":"2026-05-18T00:30:22.637439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.02268","created_at":"2026-05-18T00:30:22.637439+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKYSYXG2KE4O","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKYSYXG2KE4O7FHG","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKYSYXG2","created_at":"2026-05-18T12:30:53.716459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09970","citing_title":"Centralized Caching and Delivery of Correlated Contents over Gaussian Broadcast Channels","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKYSYXG2KE4O7FHG35T3CRTCEI","json":"https://pith.science/pith/ZKYSYXG2KE4O7FHG35T3CRTCEI.json","graph_json":"https://pith.science/api/pith-number/ZKYSYXG2KE4O7FHG35T3CRTCEI/graph.json","events_json":"https://pith.science/api/pith-number/ZKYSYXG2KE4O7FHG35T3CRTCEI/events.json","paper":"https://pith.science/paper/ZKYSYXG2"},"agent_actions":{"view_html":"https://pith.science/pith/ZKYSYXG2KE4O7FHG35T3CRTCEI","download_json":"https://pith.science/pith/ZKYSYXG2KE4O7FHG35T3CRTCEI.json","view_paper":"https://pith.science/paper/ZKYSYXG2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.02268&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKYSYXG2KE4O7FHG35T3CRTCEI/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKYSYXG2KE4O7FHG35T3CRTCEI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKYSYXG2KE4O7FHG35T3CRTCEI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKYSYXG2KE4O7FHG35T3CRTCEI/action/storage_attestation","attest_author":"https://pith.science/pith/ZKYSYXG2KE4O7FHG35T3CRTCEI/action/author_attestation","sign_citation":"https://pith.science/pith/ZKYSYXG2KE4O7FHG35T3CRTCEI/action/citation_signature","submit_replication":"https://pith.science/pith/ZKYSYXG2KE4O7FHG35T3CRTCEI/action/replication_record"}},"created_at":"2026-05-18T00:30:22.637439+00:00","updated_at":"2026-05-18T00:30:22.637439+00:00"}