{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:A3ELVCBMHYW7VJQZMVZUTIB66E","short_pith_number":"pith:A3ELVCBM","schema_version":"1.0","canonical_sha256":"06c8ba882c3e2dfaa619657349a03ef139502a995ab96e08eba5877bc274fa57","source":{"kind":"arxiv","id":"1902.01846","version":1},"attestation_state":"computed","paper":{"title":"Distribution-Dependent Analysis of Gibbs-ERM Principle","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Csaba Szepesv\\'ari, Ilja Kuzborskij, Nicol\\`o Cesa-Bianchi","submitted_at":"2019-02-05T18:31:23Z","abstract_excerpt":"Gibbs-ERM learning is a natural idealized model of learning with stochastic optimization algorithms (such as Stochastic Gradient Langevin Dynamics and ---to some extent--- Stochastic Gradient Descent), while it also arises in other contexts, including PAC-Bayesian theory, and sampling mechanisms. In this work we study the excess risk suffered by a Gibbs-ERM learner that uses non-convex, regularized empirical risk with the goal to understand the interplay between the data-generating distribution and learning in large hypothesis spaces. Our main results are distribution-dependent upper bounds 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":"1902.01846","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-05T18:31:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8a9fd44a5d1764c55fcef6837432138559369c3d52a70fb343e1bd0ceee04902","abstract_canon_sha256":"a83f435fff18a45e863add21d611a031117a1b50ce08693da9c6f75b1a25d506"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:42.195215Z","signature_b64":"xqhPp0VY7sE7xBFmzHHvuTsPnVIPBKl/NkqbQ+s6Hs3XIB62EFAj0oQZYXUkIS/UUC8KpfOdKWxX0XLaGuACDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06c8ba882c3e2dfaa619657349a03ef139502a995ab96e08eba5877bc274fa57","last_reissued_at":"2026-05-17T23:54:42.194637Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:42.194637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distribution-Dependent Analysis of Gibbs-ERM Principle","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Csaba Szepesv\\'ari, Ilja Kuzborskij, Nicol\\`o Cesa-Bianchi","submitted_at":"2019-02-05T18:31:23Z","abstract_excerpt":"Gibbs-ERM learning is a natural idealized model of learning with stochastic optimization algorithms (such as Stochastic Gradient Langevin Dynamics and ---to some extent--- Stochastic Gradient Descent), while it also arises in other contexts, including PAC-Bayesian theory, and sampling mechanisms. In this work we study the excess risk suffered by a Gibbs-ERM learner that uses non-convex, regularized empirical risk with the goal to understand the interplay between the data-generating distribution and learning in large hypothesis spaces. Our main results are distribution-dependent upper bounds on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01846","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":""},"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":"1902.01846","created_at":"2026-05-17T23:54:42.194720+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.01846v1","created_at":"2026-05-17T23:54:42.194720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01846","created_at":"2026-05-17T23:54:42.194720+00:00"},{"alias_kind":"pith_short_12","alias_value":"A3ELVCBMHYW7","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"A3ELVCBMHYW7VJQZ","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"A3ELVCBM","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.11148","citing_title":"Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Nets","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A3ELVCBMHYW7VJQZMVZUTIB66E","json":"https://pith.science/pith/A3ELVCBMHYW7VJQZMVZUTIB66E.json","graph_json":"https://pith.science/api/pith-number/A3ELVCBMHYW7VJQZMVZUTIB66E/graph.json","events_json":"https://pith.science/api/pith-number/A3ELVCBMHYW7VJQZMVZUTIB66E/events.json","paper":"https://pith.science/paper/A3ELVCBM"},"agent_actions":{"view_html":"https://pith.science/pith/A3ELVCBMHYW7VJQZMVZUTIB66E","download_json":"https://pith.science/pith/A3ELVCBMHYW7VJQZMVZUTIB66E.json","view_paper":"https://pith.science/paper/A3ELVCBM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.01846&json=true","fetch_graph":"https://pith.science/api/pith-number/A3ELVCBMHYW7VJQZMVZUTIB66E/graph.json","fetch_events":"https://pith.science/api/pith-number/A3ELVCBMHYW7VJQZMVZUTIB66E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A3ELVCBMHYW7VJQZMVZUTIB66E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A3ELVCBMHYW7VJQZMVZUTIB66E/action/storage_attestation","attest_author":"https://pith.science/pith/A3ELVCBMHYW7VJQZMVZUTIB66E/action/author_attestation","sign_citation":"https://pith.science/pith/A3ELVCBMHYW7VJQZMVZUTIB66E/action/citation_signature","submit_replication":"https://pith.science/pith/A3ELVCBMHYW7VJQZMVZUTIB66E/action/replication_record"}},"created_at":"2026-05-17T23:54:42.194720+00:00","updated_at":"2026-05-17T23:54:42.194720+00:00"}