{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:I66L3LJPBH4DNBK7WAN26YRFTN","short_pith_number":"pith:I66L3LJP","schema_version":"1.0","canonical_sha256":"47bcbdad2f09f836855fb01baf62259b75f8cb0860fa32aafaadd4a91939312d","source":{"kind":"arxiv","id":"1307.1827","version":7},"attestation_state":"computed","paper":{"title":"Loss minimization and parameter estimation with heavy tails","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Hsu, Sivan Sabato","submitted_at":"2013-07-07T01:38:16Z","abstract_excerpt":"This work studies applications and generalizations of a simple estimation technique that provides exponential concentration under heavy-tailed distributions, assuming only bounded low-order moments. We show that the technique can be used for approximate minimization of smooth and strongly convex losses, and specifically for least squares linear regression. For instance, our $d$-dimensional estimator requires just $\\tilde{O}(d\\log(1/\\delta))$ random samples to obtain a constant factor approximation to the optimal least squares loss with probability $1-\\delta$, without requiring the covariates o"},"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":"1307.1827","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-07-07T01:38:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"887072915132c0e2c28b9e3a69db85c1d54fa3bd18e8e2e351cb575bcb932d58","abstract_canon_sha256":"f10a79e4b4d5dfbb2903bd9a0f2ab199e5bfae9433f2eccf1f87e3cd474d9a54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:01.458662Z","signature_b64":"xk1vCrK7iqi3YIrq5GEGkFvrFxv6bkh0JqYltmXis+brXZIkgSZkoePVDohvy1qVuAe2bSLRkWAiJWyODJcYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47bcbdad2f09f836855fb01baf62259b75f8cb0860fa32aafaadd4a91939312d","last_reissued_at":"2026-05-18T01:17:01.457871Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:01.457871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Loss minimization and parameter estimation with heavy tails","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Hsu, Sivan Sabato","submitted_at":"2013-07-07T01:38:16Z","abstract_excerpt":"This work studies applications and generalizations of a simple estimation technique that provides exponential concentration under heavy-tailed distributions, assuming only bounded low-order moments. We show that the technique can be used for approximate minimization of smooth and strongly convex losses, and specifically for least squares linear regression. For instance, our $d$-dimensional estimator requires just $\\tilde{O}(d\\log(1/\\delta))$ random samples to obtain a constant factor approximation to the optimal least squares loss with probability $1-\\delta$, without requiring the covariates o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1307.1827","kind":"arxiv","version":7},"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":"1307.1827","created_at":"2026-05-18T01:17:01.457994+00:00"},{"alias_kind":"arxiv_version","alias_value":"1307.1827v7","created_at":"2026-05-18T01:17:01.457994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1307.1827","created_at":"2026-05-18T01:17:01.457994+00:00"},{"alias_kind":"pith_short_12","alias_value":"I66L3LJPBH4D","created_at":"2026-05-18T12:27:46.883200+00:00"},{"alias_kind":"pith_short_16","alias_value":"I66L3LJPBH4DNBK7","created_at":"2026-05-18T12:27:46.883200+00:00"},{"alias_kind":"pith_short_8","alias_value":"I66L3LJP","created_at":"2026-05-18T12:27:46.883200+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/I66L3LJPBH4DNBK7WAN26YRFTN","json":"https://pith.science/pith/I66L3LJPBH4DNBK7WAN26YRFTN.json","graph_json":"https://pith.science/api/pith-number/I66L3LJPBH4DNBK7WAN26YRFTN/graph.json","events_json":"https://pith.science/api/pith-number/I66L3LJPBH4DNBK7WAN26YRFTN/events.json","paper":"https://pith.science/paper/I66L3LJP"},"agent_actions":{"view_html":"https://pith.science/pith/I66L3LJPBH4DNBK7WAN26YRFTN","download_json":"https://pith.science/pith/I66L3LJPBH4DNBK7WAN26YRFTN.json","view_paper":"https://pith.science/paper/I66L3LJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1307.1827&json=true","fetch_graph":"https://pith.science/api/pith-number/I66L3LJPBH4DNBK7WAN26YRFTN/graph.json","fetch_events":"https://pith.science/api/pith-number/I66L3LJPBH4DNBK7WAN26YRFTN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I66L3LJPBH4DNBK7WAN26YRFTN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I66L3LJPBH4DNBK7WAN26YRFTN/action/storage_attestation","attest_author":"https://pith.science/pith/I66L3LJPBH4DNBK7WAN26YRFTN/action/author_attestation","sign_citation":"https://pith.science/pith/I66L3LJPBH4DNBK7WAN26YRFTN/action/citation_signature","submit_replication":"https://pith.science/pith/I66L3LJPBH4DNBK7WAN26YRFTN/action/replication_record"}},"created_at":"2026-05-18T01:17:01.457994+00:00","updated_at":"2026-05-18T01:17:01.457994+00:00"}