{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UUWACBQ7LONVDNNRCVDOKIVE66","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e5b6c7c35963bba7c9a05459d658baf161e58e38338ed4d144ea7830f499077b","cross_cats_sorted":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T18:00:08Z","title_canon_sha256":"b0c3cd770c5e81dbe7e8a64e8683c306fc30b452d6488d3b6a477bde136fe150"},"schema_version":"1.0","source":{"id":"2210.13497","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.13497","created_at":"2026-07-05T05:10:19Z"},{"alias_kind":"arxiv_version","alias_value":"2210.13497v1","created_at":"2026-07-05T05:10:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13497","created_at":"2026-07-05T05:10:19Z"},{"alias_kind":"pith_short_12","alias_value":"UUWACBQ7LONV","created_at":"2026-07-05T05:10:19Z"},{"alias_kind":"pith_short_16","alias_value":"UUWACBQ7LONVDNNR","created_at":"2026-07-05T05:10:19Z"},{"alias_kind":"pith_short_8","alias_value":"UUWACBQ7","created_at":"2026-07-05T05:10:19Z"}],"graph_snapshots":[{"event_id":"sha256:056ebb74fb99587451353cdcf2c2404cb541c2c3e8f36ba1f7c9479bf2988ec2","target":"graph","created_at":"2026-07-05T05:10:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2210.13497/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recovering linear subspaces from data is a fundamental and important task in statistics and machine learning. Motivated by heterogeneity in Federated Learning settings, we study a basic formulation of this problem: the principal component analysis (PCA), with a focus on dealing with irregular noise. Our data come from $n$ users with user $i$ contributing data samples from a $d$-dimensional distribution with mean $\\mu_i$. Our goal is to recover the linear subspace shared by $\\mu_1,\\ldots,\\mu_n$ using the data points from all users, where every data point from user $i$ is formed by adding an ind","authors_text":"John Duchi, Kunal Talwar, Lunjia Hu, Vitaly Feldman","cross_cats":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T18:00:08Z","title":"Subspace Recovery from Heterogeneous Data with Non-isotropic Noise"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13497","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1835b05c37772e91addf1443630988c18d4d6cb99c0c22cc424fba4dc9443aa1","target":"record","created_at":"2026-07-05T05:10:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e5b6c7c35963bba7c9a05459d658baf161e58e38338ed4d144ea7830f499077b","cross_cats_sorted":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T18:00:08Z","title_canon_sha256":"b0c3cd770c5e81dbe7e8a64e8683c306fc30b452d6488d3b6a477bde136fe150"},"schema_version":"1.0","source":{"id":"2210.13497","kind":"arxiv","version":1}},"canonical_sha256":"a52c01061f5b9b51b5b11546e522a4f7a28ef8b523109c4ad9a9105647bca624","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a52c01061f5b9b51b5b11546e522a4f7a28ef8b523109c4ad9a9105647bca624","first_computed_at":"2026-07-05T05:10:19.031355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:10:19.031355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A/X93dXYEEgsph/d8xgqmrIP0+nx76I/CC0CSZOSS71wIZtFKQojsZVpaRe6lw7HpOnndLEnrob4RwvbvpObAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:10:19.031867Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.13497","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1835b05c37772e91addf1443630988c18d4d6cb99c0c22cc424fba4dc9443aa1","sha256:056ebb74fb99587451353cdcf2c2404cb541c2c3e8f36ba1f7c9479bf2988ec2"],"state_sha256":"6b8045f53ae6bdbafe9c83f513e6a22ec45308200832eb34bc42d21b23e748a6"}