{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:PKELU5SEFUCG6RJSS3YC5DKX73","short_pith_number":"pith:PKELU5SE","schema_version":"1.0","canonical_sha256":"7a88ba76442d046f453296f02e8d57fef12480bf9a7182231d5d7be4e9929a46","source":{"kind":"arxiv","id":"1506.04855","version":2},"attestation_state":"computed","paper":{"title":"PCA with Gaussian perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Manfred K. Warmuth, Wojciech Kot{\\l}owski","submitted_at":"2015-06-16T07:04:19Z","abstract_excerpt":"Most of machine learning deals with vector parameters. Ideally we would like to take higher order information into account and make use of matrix or even tensor parameters. However the resulting algorithms are usually inefficient. Here we address on-line learning with matrix parameters. It is often easy to obtain online algorithm with good generalization performance if you eigendecompose the current parameter matrix in each trial (at a cost of $O(n^3)$ per trial). Ideally we want to avoid the decompositions and spend $O(n^2)$ per trial, i.e. linear time in the size of the matrix data. There is"},"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":"1506.04855","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-16T07:04:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d41d0c3e23e36fe32843508520865850626a26a5784ca66260ac96c06d3fcbdd","abstract_canon_sha256":"ad13401c3a58978493314d6c5f4bdd9fa8c7b5d7c2528f52aceb6f58919f9ca5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:36:22.796154Z","signature_b64":"qmNIhQz22PzPfQoNuCsRcavnmXfdZxR5p3JQZfiK7PzD7INkwqWlnuLu0URBMP/K79Ig1VyIjUniwTK/qdSKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a88ba76442d046f453296f02e8d57fef12480bf9a7182231d5d7be4e9929a46","last_reissued_at":"2026-05-18T01:36:22.795382Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:36:22.795382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PCA with Gaussian perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Manfred K. Warmuth, Wojciech Kot{\\l}owski","submitted_at":"2015-06-16T07:04:19Z","abstract_excerpt":"Most of machine learning deals with vector parameters. Ideally we would like to take higher order information into account and make use of matrix or even tensor parameters. However the resulting algorithms are usually inefficient. Here we address on-line learning with matrix parameters. It is often easy to obtain online algorithm with good generalization performance if you eigendecompose the current parameter matrix in each trial (at a cost of $O(n^3)$ per trial). Ideally we want to avoid the decompositions and spend $O(n^2)$ per trial, i.e. linear time in the size of the matrix data. There is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.04855","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":"1506.04855","created_at":"2026-05-18T01:36:22.795541+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.04855v2","created_at":"2026-05-18T01:36:22.795541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.04855","created_at":"2026-05-18T01:36:22.795541+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKELU5SEFUCG","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKELU5SEFUCG6RJS","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKELU5SE","created_at":"2026-05-18T12:29:37.295048+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/PKELU5SEFUCG6RJSS3YC5DKX73","json":"https://pith.science/pith/PKELU5SEFUCG6RJSS3YC5DKX73.json","graph_json":"https://pith.science/api/pith-number/PKELU5SEFUCG6RJSS3YC5DKX73/graph.json","events_json":"https://pith.science/api/pith-number/PKELU5SEFUCG6RJSS3YC5DKX73/events.json","paper":"https://pith.science/paper/PKELU5SE"},"agent_actions":{"view_html":"https://pith.science/pith/PKELU5SEFUCG6RJSS3YC5DKX73","download_json":"https://pith.science/pith/PKELU5SEFUCG6RJSS3YC5DKX73.json","view_paper":"https://pith.science/paper/PKELU5SE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.04855&json=true","fetch_graph":"https://pith.science/api/pith-number/PKELU5SEFUCG6RJSS3YC5DKX73/graph.json","fetch_events":"https://pith.science/api/pith-number/PKELU5SEFUCG6RJSS3YC5DKX73/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKELU5SEFUCG6RJSS3YC5DKX73/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKELU5SEFUCG6RJSS3YC5DKX73/action/storage_attestation","attest_author":"https://pith.science/pith/PKELU5SEFUCG6RJSS3YC5DKX73/action/author_attestation","sign_citation":"https://pith.science/pith/PKELU5SEFUCG6RJSS3YC5DKX73/action/citation_signature","submit_replication":"https://pith.science/pith/PKELU5SEFUCG6RJSS3YC5DKX73/action/replication_record"}},"created_at":"2026-05-18T01:36:22.795541+00:00","updated_at":"2026-05-18T01:36:22.795541+00:00"}