{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:CHAMXEMP7TWPMPL2HHFJ5WKXZL","short_pith_number":"pith:CHAMXEMP","schema_version":"1.0","canonical_sha256":"11c0cb918ffcecf63d7a39ca9ed957caf94e1750ec2423d3479fd8347a951944","source":{"kind":"arxiv","id":"1702.06976","version":1},"attestation_state":"computed","paper":{"title":"Heavy-Tailed Analogues of the Covariance Matrix for ICA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anupama Nandi, Joseph Anderson, Luis Rademacher, Navin Goyal","submitted_at":"2017-02-22T19:27:38Z","abstract_excerpt":"Independent Component Analysis (ICA) is the problem of learning a square matrix $A$, given samples of $X=AS$, where $S$ is a random vector with independent coordinates. Most existing algorithms are provably efficient only when each $S_i$ has finite and moderately valued fourth moment. However, there are practical applications where this assumption need not be true, such as speech and finance. Algorithms have been proposed for heavy-tailed ICA, but they are not practical, using random walks and the full power of the ellipsoid algorithm multiple times. The main contributions of this paper are:\n "},"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":"1702.06976","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-22T19:27:38Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2da6c9919427a4818c08b168dc4b7bf5a37035cd3f860ae2a25498097863721e","abstract_canon_sha256":"1a421e66e6b0be498c912166e4e85017e08449b832d6a42972ca108da739ee89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:08.821759Z","signature_b64":"jKpgnejxJxFV3J7W/Od846pKdRIo5o6EY4OWUY7X0M1ekil7WKxMc5gbyGUVoN7t5ftg5hOY2uP+2xeOIJqADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11c0cb918ffcecf63d7a39ca9ed957caf94e1750ec2423d3479fd8347a951944","last_reissued_at":"2026-05-18T00:50:08.821077Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:08.821077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heavy-Tailed Analogues of the Covariance Matrix for ICA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anupama Nandi, Joseph Anderson, Luis Rademacher, Navin Goyal","submitted_at":"2017-02-22T19:27:38Z","abstract_excerpt":"Independent Component Analysis (ICA) is the problem of learning a square matrix $A$, given samples of $X=AS$, where $S$ is a random vector with independent coordinates. Most existing algorithms are provably efficient only when each $S_i$ has finite and moderately valued fourth moment. However, there are practical applications where this assumption need not be true, such as speech and finance. Algorithms have been proposed for heavy-tailed ICA, but they are not practical, using random walks and the full power of the ellipsoid algorithm multiple times. The main contributions of this paper are:\n "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.06976","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":""},"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":"1702.06976","created_at":"2026-05-18T00:50:08.821178+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.06976v1","created_at":"2026-05-18T00:50:08.821178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.06976","created_at":"2026-05-18T00:50:08.821178+00:00"},{"alias_kind":"pith_short_12","alias_value":"CHAMXEMP7TWP","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"CHAMXEMP7TWPMPL2","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"CHAMXEMP","created_at":"2026-05-18T12:31:10.602751+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/CHAMXEMP7TWPMPL2HHFJ5WKXZL","json":"https://pith.science/pith/CHAMXEMP7TWPMPL2HHFJ5WKXZL.json","graph_json":"https://pith.science/api/pith-number/CHAMXEMP7TWPMPL2HHFJ5WKXZL/graph.json","events_json":"https://pith.science/api/pith-number/CHAMXEMP7TWPMPL2HHFJ5WKXZL/events.json","paper":"https://pith.science/paper/CHAMXEMP"},"agent_actions":{"view_html":"https://pith.science/pith/CHAMXEMP7TWPMPL2HHFJ5WKXZL","download_json":"https://pith.science/pith/CHAMXEMP7TWPMPL2HHFJ5WKXZL.json","view_paper":"https://pith.science/paper/CHAMXEMP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.06976&json=true","fetch_graph":"https://pith.science/api/pith-number/CHAMXEMP7TWPMPL2HHFJ5WKXZL/graph.json","fetch_events":"https://pith.science/api/pith-number/CHAMXEMP7TWPMPL2HHFJ5WKXZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CHAMXEMP7TWPMPL2HHFJ5WKXZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CHAMXEMP7TWPMPL2HHFJ5WKXZL/action/storage_attestation","attest_author":"https://pith.science/pith/CHAMXEMP7TWPMPL2HHFJ5WKXZL/action/author_attestation","sign_citation":"https://pith.science/pith/CHAMXEMP7TWPMPL2HHFJ5WKXZL/action/citation_signature","submit_replication":"https://pith.science/pith/CHAMXEMP7TWPMPL2HHFJ5WKXZL/action/replication_record"}},"created_at":"2026-05-18T00:50:08.821178+00:00","updated_at":"2026-05-18T00:50:08.821178+00:00"}