{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:ZRE6BLWX3DKSRG36LBSWQIOJYJ","short_pith_number":"pith:ZRE6BLWX","schema_version":"1.0","canonical_sha256":"cc49e0aed7d8d5289b7e58656821c9c27075c0cabdae7ad51859ace9354a2e7a","source":{"kind":"arxiv","id":"1306.3895","version":2},"attestation_state":"computed","paper":{"title":"On-line PCA with Optimal Regrets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiazhong Nie, Manfred K. Warmuth, Wojciech Kotlowski","submitted_at":"2013-06-17T15:29:00Z","abstract_excerpt":"We carefully investigate the on-line version of PCA, where in each trial a learning algorithm plays a k-dimensional subspace, and suffers the compression loss on the next instance when projected into the chosen subspace. In this setting, we analyze two popular on-line algorithms, Gradient Descent (GD) and Exponentiated Gradient (EG). We show that both algorithms are essentially optimal in the worst-case. This comes as a surprise, since EG is known to perform sub-optimally when the instances are sparse. This different behavior of EG for PCA is mainly related to the non-negativity of the loss in"},"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":"1306.3895","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-06-17T15:29:00Z","cross_cats_sorted":[],"title_canon_sha256":"b3e4f83e56d5f0c202b4cda63457982f99a7f8e01992e0ac04e388cb0869242e","abstract_canon_sha256":"9db052c2540146a3d1079a36f0420345e7049a50180f5e84d616c161540d06dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:52:14.406640Z","signature_b64":"9cmfaQanGswcsfORGpLHxNrQ6gfcKeS5yC2Zccn1CoWiB8KqeEJV7eY+ZBR1B8YImaHBDi+W9YT5UqITPZYOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc49e0aed7d8d5289b7e58656821c9c27075c0cabdae7ad51859ace9354a2e7a","last_reissued_at":"2026-05-18T02:52:14.406165Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:52:14.406165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On-line PCA with Optimal Regrets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiazhong Nie, Manfred K. Warmuth, Wojciech Kotlowski","submitted_at":"2013-06-17T15:29:00Z","abstract_excerpt":"We carefully investigate the on-line version of PCA, where in each trial a learning algorithm plays a k-dimensional subspace, and suffers the compression loss on the next instance when projected into the chosen subspace. In this setting, we analyze two popular on-line algorithms, Gradient Descent (GD) and Exponentiated Gradient (EG). We show that both algorithms are essentially optimal in the worst-case. This comes as a surprise, since EG is known to perform sub-optimally when the instances are sparse. This different behavior of EG for PCA is mainly related to the non-negativity of the loss in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1306.3895","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":""},"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":"1306.3895","created_at":"2026-05-18T02:52:14.406240+00:00"},{"alias_kind":"arxiv_version","alias_value":"1306.3895v2","created_at":"2026-05-18T02:52:14.406240+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1306.3895","created_at":"2026-05-18T02:52:14.406240+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRE6BLWX3DKS","created_at":"2026-05-18T12:28:09.283467+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRE6BLWX3DKSRG36","created_at":"2026-05-18T12:28:09.283467+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRE6BLWX","created_at":"2026-05-18T12:28:09.283467+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/ZRE6BLWX3DKSRG36LBSWQIOJYJ","json":"https://pith.science/pith/ZRE6BLWX3DKSRG36LBSWQIOJYJ.json","graph_json":"https://pith.science/api/pith-number/ZRE6BLWX3DKSRG36LBSWQIOJYJ/graph.json","events_json":"https://pith.science/api/pith-number/ZRE6BLWX3DKSRG36LBSWQIOJYJ/events.json","paper":"https://pith.science/paper/ZRE6BLWX"},"agent_actions":{"view_html":"https://pith.science/pith/ZRE6BLWX3DKSRG36LBSWQIOJYJ","download_json":"https://pith.science/pith/ZRE6BLWX3DKSRG36LBSWQIOJYJ.json","view_paper":"https://pith.science/paper/ZRE6BLWX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1306.3895&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRE6BLWX3DKSRG36LBSWQIOJYJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRE6BLWX3DKSRG36LBSWQIOJYJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRE6BLWX3DKSRG36LBSWQIOJYJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRE6BLWX3DKSRG36LBSWQIOJYJ/action/storage_attestation","attest_author":"https://pith.science/pith/ZRE6BLWX3DKSRG36LBSWQIOJYJ/action/author_attestation","sign_citation":"https://pith.science/pith/ZRE6BLWX3DKSRG36LBSWQIOJYJ/action/citation_signature","submit_replication":"https://pith.science/pith/ZRE6BLWX3DKSRG36LBSWQIOJYJ/action/replication_record"}},"created_at":"2026-05-18T02:52:14.406240+00:00","updated_at":"2026-05-18T02:52:14.406240+00:00"}