{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:CHI5O2DGJQJKKHVQR6SODRHZ52","short_pith_number":"pith:CHI5O2DG","schema_version":"1.0","canonical_sha256":"11d1d768664c12a51eb08fa4e1c4f9ee846a872c66f2c4150cf39c40c3ca7a8f","source":{"kind":"arxiv","id":"1705.07809","version":2},"attestation_state":"computed","paper":{"title":"Information-theoretic analysis of generalization capability of learning algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aolin Xu, Maxim Raginsky","submitted_at":"2017-05-22T15:38:22Z","abstract_excerpt":"We derive upper bounds on the generalization error of a learning algorithm in terms of the mutual information between its input and output. The bounds provide an information-theoretic understanding of generalization in learning problems, and give theoretical guidelines for striking the right balance between data fit and generalization by controlling the input-output mutual information. We propose a number of methods for this purpose, among which are algorithms that regularize the ERM algorithm with relative entropy or with random noise. Our work extends and leads to nontrivial improvements on "},"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":"1705.07809","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-22T15:38:22Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"7a291dd5037f58a0ecccee84c6e5e15cc5aedc2ff2e27f27f07d34fd75686ba9","abstract_canon_sha256":"78fc48b24896a6c6c7becb690b4c036d789cd724a2c68f37c9b3b1b29b36e006"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:19.450229Z","signature_b64":"LJttK4I04Ng+j1nk9G7JknMYuKOGUs+Fu8YHRuoc1jxIhbWvJk34pJ6rm/cUL7VNFi7hUg+0Hil7W4WZu++6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11d1d768664c12a51eb08fa4e1c4f9ee846a872c66f2c4150cf39c40c3ca7a8f","last_reissued_at":"2026-05-18T00:31:19.449441Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:19.449441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Information-theoretic analysis of generalization capability of learning algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aolin Xu, Maxim Raginsky","submitted_at":"2017-05-22T15:38:22Z","abstract_excerpt":"We derive upper bounds on the generalization error of a learning algorithm in terms of the mutual information between its input and output. The bounds provide an information-theoretic understanding of generalization in learning problems, and give theoretical guidelines for striking the right balance between data fit and generalization by controlling the input-output mutual information. We propose a number of methods for this purpose, among which are algorithms that regularize the ERM algorithm with relative entropy or with random noise. Our work extends and leads to nontrivial improvements on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07809","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":"1705.07809","created_at":"2026-05-18T00:31:19.449568+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.07809v2","created_at":"2026-05-18T00:31:19.449568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07809","created_at":"2026-05-18T00:31:19.449568+00:00"},{"alias_kind":"pith_short_12","alias_value":"CHI5O2DGJQJK","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"CHI5O2DGJQJKKHVQ","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"CHI5O2DG","created_at":"2026-05-18T12:31:10.602751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13143","citing_title":"On the Generalization of Knowledge Distillation: An Information-Theoretic View","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06281","citing_title":"Generalization error bounds for two-layer neural networks with Lipschitz loss function","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CHI5O2DGJQJKKHVQR6SODRHZ52","json":"https://pith.science/pith/CHI5O2DGJQJKKHVQR6SODRHZ52.json","graph_json":"https://pith.science/api/pith-number/CHI5O2DGJQJKKHVQR6SODRHZ52/graph.json","events_json":"https://pith.science/api/pith-number/CHI5O2DGJQJKKHVQR6SODRHZ52/events.json","paper":"https://pith.science/paper/CHI5O2DG"},"agent_actions":{"view_html":"https://pith.science/pith/CHI5O2DGJQJKKHVQR6SODRHZ52","download_json":"https://pith.science/pith/CHI5O2DGJQJKKHVQR6SODRHZ52.json","view_paper":"https://pith.science/paper/CHI5O2DG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.07809&json=true","fetch_graph":"https://pith.science/api/pith-number/CHI5O2DGJQJKKHVQR6SODRHZ52/graph.json","fetch_events":"https://pith.science/api/pith-number/CHI5O2DGJQJKKHVQR6SODRHZ52/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CHI5O2DGJQJKKHVQR6SODRHZ52/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CHI5O2DGJQJKKHVQR6SODRHZ52/action/storage_attestation","attest_author":"https://pith.science/pith/CHI5O2DGJQJKKHVQR6SODRHZ52/action/author_attestation","sign_citation":"https://pith.science/pith/CHI5O2DGJQJKKHVQR6SODRHZ52/action/citation_signature","submit_replication":"https://pith.science/pith/CHI5O2DGJQJKKHVQR6SODRHZ52/action/replication_record"}},"created_at":"2026-05-18T00:31:19.449568+00:00","updated_at":"2026-05-18T00:31:19.449568+00:00"}