{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IETFUZFHUWQ7VBGXYWAYTKU4ZT","short_pith_number":"pith:IETFUZFH","schema_version":"1.0","canonical_sha256":"41265a64a7a5a1fa84d7c58189aa9cccc8ab6f5c8df15b9ea545fde8a21589b3","source":{"kind":"arxiv","id":"2309.02698","version":1},"attestation_state":"computed","paper":{"title":"Quantile and pseudo-Huber Tensor Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ME","stat.TH"],"primary_cat":"math.ST","authors_text":"Dong Xia, Yinan Shen","submitted_at":"2023-09-06T04:21:50Z","abstract_excerpt":"This paper studies the computational and statistical aspects of quantile and pseudo-Huber tensor decomposition. The integrated investigation of computational and statistical issues of robust tensor decomposition poses challenges due to the non-smooth loss functions. We propose a projected sub-gradient descent algorithm for tensor decomposition, equipped with either the pseudo-Huber loss or the quantile loss. In the presence of both heavy-tailed noise and Huber's contamination error, we demonstrate that our algorithm exhibits a so-called phenomenon of two-phase convergence with a carefully chos"},"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":"2309.02698","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2023-09-06T04:21:50Z","cross_cats_sorted":["cs.IT","math.IT","stat.ME","stat.TH"],"title_canon_sha256":"10c8e9b2bbb9b2eaf49ed8918b54ae465cc49deb74c967fac933e53bc6076fb5","abstract_canon_sha256":"d1f6bc5925a29a0463495abea35935a8e6c7f2bb9dcb205cb403205417e3ea5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:16.029768Z","signature_b64":"rlMSl6UV9Mlmxrrk7SAVk4RCWnfmbtVXzMUjFdAKtn7jeIvU4yDSDNvlsv0QI5vj1ZVWkiknYfTeL6ATFfMSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41265a64a7a5a1fa84d7c58189aa9cccc8ab6f5c8df15b9ea545fde8a21589b3","last_reissued_at":"2026-07-05T06:48:16.029392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:16.029392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantile and pseudo-Huber Tensor Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ME","stat.TH"],"primary_cat":"math.ST","authors_text":"Dong Xia, Yinan Shen","submitted_at":"2023-09-06T04:21:50Z","abstract_excerpt":"This paper studies the computational and statistical aspects of quantile and pseudo-Huber tensor decomposition. The integrated investigation of computational and statistical issues of robust tensor decomposition poses challenges due to the non-smooth loss functions. We propose a projected sub-gradient descent algorithm for tensor decomposition, equipped with either the pseudo-Huber loss or the quantile loss. In the presence of both heavy-tailed noise and Huber's contamination error, we demonstrate that our algorithm exhibits a so-called phenomenon of two-phase convergence with a carefully chos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02698","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.02698/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2309.02698","created_at":"2026-07-05T06:48:16.029446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.02698v1","created_at":"2026-07-05T06:48:16.029446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02698","created_at":"2026-07-05T06:48:16.029446+00:00"},{"alias_kind":"pith_short_12","alias_value":"IETFUZFHUWQ7","created_at":"2026-07-05T06:48:16.029446+00:00"},{"alias_kind":"pith_short_16","alias_value":"IETFUZFHUWQ7VBGX","created_at":"2026-07-05T06:48:16.029446+00:00"},{"alias_kind":"pith_short_8","alias_value":"IETFUZFH","created_at":"2026-07-05T06:48:16.029446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16223","citing_title":"Statistical Inference for Low-Rank Tensor Models","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IETFUZFHUWQ7VBGXYWAYTKU4ZT","json":"https://pith.science/pith/IETFUZFHUWQ7VBGXYWAYTKU4ZT.json","graph_json":"https://pith.science/api/pith-number/IETFUZFHUWQ7VBGXYWAYTKU4ZT/graph.json","events_json":"https://pith.science/api/pith-number/IETFUZFHUWQ7VBGXYWAYTKU4ZT/events.json","paper":"https://pith.science/paper/IETFUZFH"},"agent_actions":{"view_html":"https://pith.science/pith/IETFUZFHUWQ7VBGXYWAYTKU4ZT","download_json":"https://pith.science/pith/IETFUZFHUWQ7VBGXYWAYTKU4ZT.json","view_paper":"https://pith.science/paper/IETFUZFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.02698&json=true","fetch_graph":"https://pith.science/api/pith-number/IETFUZFHUWQ7VBGXYWAYTKU4ZT/graph.json","fetch_events":"https://pith.science/api/pith-number/IETFUZFHUWQ7VBGXYWAYTKU4ZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IETFUZFHUWQ7VBGXYWAYTKU4ZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IETFUZFHUWQ7VBGXYWAYTKU4ZT/action/storage_attestation","attest_author":"https://pith.science/pith/IETFUZFHUWQ7VBGXYWAYTKU4ZT/action/author_attestation","sign_citation":"https://pith.science/pith/IETFUZFHUWQ7VBGXYWAYTKU4ZT/action/citation_signature","submit_replication":"https://pith.science/pith/IETFUZFHUWQ7VBGXYWAYTKU4ZT/action/replication_record"}},"created_at":"2026-07-05T06:48:16.029446+00:00","updated_at":"2026-07-05T06:48:16.029446+00:00"}