{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6QS5IJKDTFHYIT3EQFUBDMQVFY","short_pith_number":"pith:6QS5IJKD","schema_version":"1.0","canonical_sha256":"f425d42543994f844f64816811b2152e071760a04f52530ef40a865d6a7c3c68","source":{"kind":"arxiv","id":"2205.13827","version":2},"attestation_state":"computed","paper":{"title":"Error Bound of Empirical $\\ell_2$ Risk Minimization for Noisy Standard and Generalized Phase Retrieval Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Junren Chen, Michael K. Ng","submitted_at":"2022-05-27T08:38:33Z","abstract_excerpt":"In this paper, we study the estimation performance of empirical $\\ell_2$ risk minimization (ERM) in noisy (standard) phase retrieval (NPR) given by $y_k = |\\alpha_k^*x_0|^2+\\eta_k$, or noisy generalized phase retrieval (NGPR) formulated as $y_k = x_0^*A_kx_0 + \\eta_k$, where $x_0\\in\\mathbb{K}^d$ is the desired signal, $n$ is the sample size, $\\eta= (\\eta_1,...,\\eta_n)^\\top$ is the noise vector. We establish new error bounds under different noise patterns, and our proofs are valid for both $\\mathbb{K}=\\mathbb{R}$ and $\\mathbb{K}=\\mathbb{C}$. In NPR under arbitrary noise vector $\\eta$, we derive"},"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":"2205.13827","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-05-27T08:38:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3357c8a12192a23982824bc8fe6720fd3dd1b42b5265471437da404fafbe1b4b","abstract_canon_sha256":"436251b9dd02c36c198bc0591ba461db967df7b7dd3fd6ff284c1d827cf1adeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:35:21.365842Z","signature_b64":"cfGUwbOr2LnFuJS3ag2QPOgsgdoaMFnEckYN3elr2xZR/veELVtn9YOUQjwqVzJDkD5kL+JfFzaSp221vHokBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f425d42543994f844f64816811b2152e071760a04f52530ef40a865d6a7c3c68","last_reissued_at":"2026-07-05T04:35:21.365337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:35:21.365337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Error Bound of Empirical $\\ell_2$ Risk Minimization for Noisy Standard and Generalized Phase Retrieval Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Junren Chen, Michael K. Ng","submitted_at":"2022-05-27T08:38:33Z","abstract_excerpt":"In this paper, we study the estimation performance of empirical $\\ell_2$ risk minimization (ERM) in noisy (standard) phase retrieval (NPR) given by $y_k = |\\alpha_k^*x_0|^2+\\eta_k$, or noisy generalized phase retrieval (NGPR) formulated as $y_k = x_0^*A_kx_0 + \\eta_k$, where $x_0\\in\\mathbb{K}^d$ is the desired signal, $n$ is the sample size, $\\eta= (\\eta_1,...,\\eta_n)^\\top$ is the noise vector. We establish new error bounds under different noise patterns, and our proofs are valid for both $\\mathbb{K}=\\mathbb{R}$ and $\\mathbb{K}=\\mathbb{C}$. In NPR under arbitrary noise vector $\\eta$, we derive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13827","kind":"arxiv","version":2},"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/2205.13827/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":"2205.13827","created_at":"2026-07-05T04:35:21.365397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.13827v2","created_at":"2026-07-05T04:35:21.365397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13827","created_at":"2026-07-05T04:35:21.365397+00:00"},{"alias_kind":"pith_short_12","alias_value":"6QS5IJKDTFHY","created_at":"2026-07-05T04:35:21.365397+00:00"},{"alias_kind":"pith_short_16","alias_value":"6QS5IJKDTFHYIT3E","created_at":"2026-07-05T04:35:21.365397+00:00"},{"alias_kind":"pith_short_8","alias_value":"6QS5IJKD","created_at":"2026-07-05T04:35:21.365397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.17946","citing_title":"Geometric Characteristics and Stable Guarantees for Phaseless Operators and Structured Matrix Restoration","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6QS5IJKDTFHYIT3EQFUBDMQVFY","json":"https://pith.science/pith/6QS5IJKDTFHYIT3EQFUBDMQVFY.json","graph_json":"https://pith.science/api/pith-number/6QS5IJKDTFHYIT3EQFUBDMQVFY/graph.json","events_json":"https://pith.science/api/pith-number/6QS5IJKDTFHYIT3EQFUBDMQVFY/events.json","paper":"https://pith.science/paper/6QS5IJKD"},"agent_actions":{"view_html":"https://pith.science/pith/6QS5IJKDTFHYIT3EQFUBDMQVFY","download_json":"https://pith.science/pith/6QS5IJKDTFHYIT3EQFUBDMQVFY.json","view_paper":"https://pith.science/paper/6QS5IJKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.13827&json=true","fetch_graph":"https://pith.science/api/pith-number/6QS5IJKDTFHYIT3EQFUBDMQVFY/graph.json","fetch_events":"https://pith.science/api/pith-number/6QS5IJKDTFHYIT3EQFUBDMQVFY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6QS5IJKDTFHYIT3EQFUBDMQVFY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6QS5IJKDTFHYIT3EQFUBDMQVFY/action/storage_attestation","attest_author":"https://pith.science/pith/6QS5IJKDTFHYIT3EQFUBDMQVFY/action/author_attestation","sign_citation":"https://pith.science/pith/6QS5IJKDTFHYIT3EQFUBDMQVFY/action/citation_signature","submit_replication":"https://pith.science/pith/6QS5IJKDTFHYIT3EQFUBDMQVFY/action/replication_record"}},"created_at":"2026-07-05T04:35:21.365397+00:00","updated_at":"2026-07-05T04:35:21.365397+00:00"}