{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5J24ESTBUF47ZRQDZYBKG5FQIU","short_pith_number":"pith:5J24ESTB","schema_version":"1.0","canonical_sha256":"ea75c24a61a179fcc603ce02a374b0452569e8eee02743f36d38a98a2734e78d","source":{"kind":"arxiv","id":"1805.00616","version":4},"attestation_state":"computed","paper":{"title":"$\\ell_1$-regression with Heavy-tailed Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lijun Zhang, Zhi-Hua Zhou","submitted_at":"2018-05-02T04:05:19Z","abstract_excerpt":"In this paper, we consider the problem of linear regression with heavy-tailed distributions. Different from previous studies that use the squared loss to measure the performance, we choose the absolute loss, which is capable of estimating the conditional median. To address the challenge that both the input and output could be heavy-tailed, we propose a truncated minimization problem, and demonstrate that it enjoys an $\\widetilde{O}(\\sqrt{d/n})$ excess risk, where $d$ is the dimensionality and $n$ is the number of samples. Compared with traditional work on $\\ell_1$-regression, the main advantag"},"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":"1805.00616","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-02T04:05:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f38e2d0081580a4f8e786ca0afb2fe2586dc2fb661b6649edcb0aaad563e2b30","abstract_canon_sha256":"8563c5260b58a7b879360933ad4dabc34cbcd78c4aa08ffbb7d30409161e1882"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:19.390846Z","signature_b64":"TCK1yWJUaJ7WGyuXqL0+iQTFbHr9WKzQAz+dCuJXJyhJmBhimC4aqBV4B07GBDZD7vm6Jt/RDU0mo4PGwjkWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea75c24a61a179fcc603ce02a374b0452569e8eee02743f36d38a98a2734e78d","last_reissued_at":"2026-05-18T00:02:19.390373Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:19.390373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$\\ell_1$-regression with Heavy-tailed Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lijun Zhang, Zhi-Hua Zhou","submitted_at":"2018-05-02T04:05:19Z","abstract_excerpt":"In this paper, we consider the problem of linear regression with heavy-tailed distributions. Different from previous studies that use the squared loss to measure the performance, we choose the absolute loss, which is capable of estimating the conditional median. To address the challenge that both the input and output could be heavy-tailed, we propose a truncated minimization problem, and demonstrate that it enjoys an $\\widetilde{O}(\\sqrt{d/n})$ excess risk, where $d$ is the dimensionality and $n$ is the number of samples. Compared with traditional work on $\\ell_1$-regression, the main advantag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00616","kind":"arxiv","version":4},"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":"1805.00616","created_at":"2026-05-18T00:02:19.390448+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.00616v4","created_at":"2026-05-18T00:02:19.390448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00616","created_at":"2026-05-18T00:02:19.390448+00:00"},{"alias_kind":"pith_short_12","alias_value":"5J24ESTBUF47","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5J24ESTBUF47ZRQD","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5J24ESTB","created_at":"2026-05-18T12:32:08.215937+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/5J24ESTBUF47ZRQDZYBKG5FQIU","json":"https://pith.science/pith/5J24ESTBUF47ZRQDZYBKG5FQIU.json","graph_json":"https://pith.science/api/pith-number/5J24ESTBUF47ZRQDZYBKG5FQIU/graph.json","events_json":"https://pith.science/api/pith-number/5J24ESTBUF47ZRQDZYBKG5FQIU/events.json","paper":"https://pith.science/paper/5J24ESTB"},"agent_actions":{"view_html":"https://pith.science/pith/5J24ESTBUF47ZRQDZYBKG5FQIU","download_json":"https://pith.science/pith/5J24ESTBUF47ZRQDZYBKG5FQIU.json","view_paper":"https://pith.science/paper/5J24ESTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.00616&json=true","fetch_graph":"https://pith.science/api/pith-number/5J24ESTBUF47ZRQDZYBKG5FQIU/graph.json","fetch_events":"https://pith.science/api/pith-number/5J24ESTBUF47ZRQDZYBKG5FQIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5J24ESTBUF47ZRQDZYBKG5FQIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5J24ESTBUF47ZRQDZYBKG5FQIU/action/storage_attestation","attest_author":"https://pith.science/pith/5J24ESTBUF47ZRQDZYBKG5FQIU/action/author_attestation","sign_citation":"https://pith.science/pith/5J24ESTBUF47ZRQDZYBKG5FQIU/action/citation_signature","submit_replication":"https://pith.science/pith/5J24ESTBUF47ZRQDZYBKG5FQIU/action/replication_record"}},"created_at":"2026-05-18T00:02:19.390448+00:00","updated_at":"2026-05-18T00:02:19.390448+00:00"}