{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:UEU4G2Z7QEQUYO4EVAIRDFRHEC","short_pith_number":"pith:UEU4G2Z7","schema_version":"1.0","canonical_sha256":"a129c36b3f81214c3b84a81111962720a4b82cdba73670825c13264186b630e9","source":{"kind":"arxiv","id":"1702.08249","version":1},"attestation_state":"computed","paper":{"title":"Uniform Deviation Bounds for Unbounded Loss Functions like k-Means","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andreas Krause, Mario Lucic, Olivier Bachem, S. Hamed Hassani","submitted_at":"2017-02-27T12:03:41Z","abstract_excerpt":"Uniform deviation bounds limit the difference between a model's expected loss and its loss on an empirical sample uniformly for all models in a learning problem. As such, they are a critical component to empirical risk minimization. In this paper, we provide a novel framework to obtain uniform deviation bounds for loss functions which are *unbounded*. In our main application, this allows us to obtain bounds for $k$-Means clustering under weak assumptions on the underlying distribution. If the fourth moment is bounded, we prove a rate of $\\mathcal{O}\\left(m^{-\\frac12}\\right)$ compared to the pr"},"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":"1702.08249","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-02-27T12:03:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5524e7a66fa8992664475c0026c3488f23c2e2ceb3c5ce3f63c4ce17d53786f8","abstract_canon_sha256":"9fc9cf3d184cf8db0d6b738b95d078fe343e2dbd1d800af9ccbb7b3f49a5892f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:55.455361Z","signature_b64":"WTXpHkG0X2BaxMoBbq5hR2B6mF2+s9HNpulAZ8aijAWTQYlAPUNg1GRc9NFz54nPNUIafhIJWHFzF7wH2J0cDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a129c36b3f81214c3b84a81111962720a4b82cdba73670825c13264186b630e9","last_reissued_at":"2026-05-18T00:49:55.454567Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:55.454567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uniform Deviation Bounds for Unbounded Loss Functions like k-Means","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andreas Krause, Mario Lucic, Olivier Bachem, S. Hamed Hassani","submitted_at":"2017-02-27T12:03:41Z","abstract_excerpt":"Uniform deviation bounds limit the difference between a model's expected loss and its loss on an empirical sample uniformly for all models in a learning problem. As such, they are a critical component to empirical risk minimization. In this paper, we provide a novel framework to obtain uniform deviation bounds for loss functions which are *unbounded*. In our main application, this allows us to obtain bounds for $k$-Means clustering under weak assumptions on the underlying distribution. If the fourth moment is bounded, we prove a rate of $\\mathcal{O}\\left(m^{-\\frac12}\\right)$ compared to the pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08249","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":"1702.08249","created_at":"2026-05-18T00:49:55.454674+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.08249v1","created_at":"2026-05-18T00:49:55.454674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08249","created_at":"2026-05-18T00:49:55.454674+00:00"},{"alias_kind":"pith_short_12","alias_value":"UEU4G2Z7QEQU","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"UEU4G2Z7QEQUYO4E","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"UEU4G2Z7","created_at":"2026-05-18T12:31:46.661854+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/UEU4G2Z7QEQUYO4EVAIRDFRHEC","json":"https://pith.science/pith/UEU4G2Z7QEQUYO4EVAIRDFRHEC.json","graph_json":"https://pith.science/api/pith-number/UEU4G2Z7QEQUYO4EVAIRDFRHEC/graph.json","events_json":"https://pith.science/api/pith-number/UEU4G2Z7QEQUYO4EVAIRDFRHEC/events.json","paper":"https://pith.science/paper/UEU4G2Z7"},"agent_actions":{"view_html":"https://pith.science/pith/UEU4G2Z7QEQUYO4EVAIRDFRHEC","download_json":"https://pith.science/pith/UEU4G2Z7QEQUYO4EVAIRDFRHEC.json","view_paper":"https://pith.science/paper/UEU4G2Z7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.08249&json=true","fetch_graph":"https://pith.science/api/pith-number/UEU4G2Z7QEQUYO4EVAIRDFRHEC/graph.json","fetch_events":"https://pith.science/api/pith-number/UEU4G2Z7QEQUYO4EVAIRDFRHEC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UEU4G2Z7QEQUYO4EVAIRDFRHEC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UEU4G2Z7QEQUYO4EVAIRDFRHEC/action/storage_attestation","attest_author":"https://pith.science/pith/UEU4G2Z7QEQUYO4EVAIRDFRHEC/action/author_attestation","sign_citation":"https://pith.science/pith/UEU4G2Z7QEQUYO4EVAIRDFRHEC/action/citation_signature","submit_replication":"https://pith.science/pith/UEU4G2Z7QEQUYO4EVAIRDFRHEC/action/replication_record"}},"created_at":"2026-05-18T00:49:55.454674+00:00","updated_at":"2026-05-18T00:49:55.454674+00:00"}