{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IRMXBJGCF6SFN23SG7AX66UQLS","short_pith_number":"pith:IRMXBJGC","schema_version":"1.0","canonical_sha256":"445970a4c22fa456eb7237c17f7a905c8a5c187844957b194a13be69caaacaa4","source":{"kind":"arxiv","id":"2110.13970","version":3},"attestation_state":"computed","paper":{"title":"Rademacher Random Projections with Tensor Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Beheshteh T. Rakhshan, Guillaume Rabusseau","submitted_at":"2021-10-26T19:18:20Z","abstract_excerpt":"Random projection (RP) have recently emerged as popular techniques in the machine learning community for their ability in reducing the dimension of very high-dimensional tensors. Following the work in [30], we consider a tensorized random projection relying on Tensor Train (TT) decomposition where each element of the core tensors is drawn from a Rademacher distribution. Our theoretical results reveal that the Gaussian low-rank tensor represented in compressed form in TT format in [30] can be replaced by a TT tensor with core elements drawn from a Rademacher distribution with the same embedding"},"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":"2110.13970","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-26T19:18:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"52d21ed67af3b28c63994c5a8ffd9e786ee022cc4d966dbe979941ae863d150f","abstract_canon_sha256":"7b8557db701825a8080f2f05602d5a02f2b93d3c81355fd49cba8f40eb95a432"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:53:49.952730Z","signature_b64":"n4Vf0Dik4UxpBnaEk6KEuh+aqcqUcd48SHwEFoPP4iy0Smg5FMFK+ZwiK1mLudO0U7EUvsjckPQaJo1jcoTXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"445970a4c22fa456eb7237c17f7a905c8a5c187844957b194a13be69caaacaa4","last_reissued_at":"2026-07-05T03:53:49.952263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:53:49.952263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rademacher Random Projections with Tensor Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Beheshteh T. Rakhshan, Guillaume Rabusseau","submitted_at":"2021-10-26T19:18:20Z","abstract_excerpt":"Random projection (RP) have recently emerged as popular techniques in the machine learning community for their ability in reducing the dimension of very high-dimensional tensors. Following the work in [30], we consider a tensorized random projection relying on Tensor Train (TT) decomposition where each element of the core tensors is drawn from a Rademacher distribution. Our theoretical results reveal that the Gaussian low-rank tensor represented in compressed form in TT format in [30] can be replaced by a TT tensor with core elements drawn from a Rademacher distribution with the same embedding"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.13970","kind":"arxiv","version":3},"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/2110.13970/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":"2110.13970","created_at":"2026-07-05T03:53:49.952321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.13970v3","created_at":"2026-07-05T03:53:49.952321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.13970","created_at":"2026-07-05T03:53:49.952321+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRMXBJGCF6SF","created_at":"2026-07-05T03:53:49.952321+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRMXBJGCF6SFN23S","created_at":"2026-07-05T03:53:49.952321+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRMXBJGC","created_at":"2026-07-05T03:53:49.952321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21189","citing_title":"Faster Linear Algebra Algorithms with Structured Random Matrices","ref_index":100,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IRMXBJGCF6SFN23SG7AX66UQLS","json":"https://pith.science/pith/IRMXBJGCF6SFN23SG7AX66UQLS.json","graph_json":"https://pith.science/api/pith-number/IRMXBJGCF6SFN23SG7AX66UQLS/graph.json","events_json":"https://pith.science/api/pith-number/IRMXBJGCF6SFN23SG7AX66UQLS/events.json","paper":"https://pith.science/paper/IRMXBJGC"},"agent_actions":{"view_html":"https://pith.science/pith/IRMXBJGCF6SFN23SG7AX66UQLS","download_json":"https://pith.science/pith/IRMXBJGCF6SFN23SG7AX66UQLS.json","view_paper":"https://pith.science/paper/IRMXBJGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.13970&json=true","fetch_graph":"https://pith.science/api/pith-number/IRMXBJGCF6SFN23SG7AX66UQLS/graph.json","fetch_events":"https://pith.science/api/pith-number/IRMXBJGCF6SFN23SG7AX66UQLS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRMXBJGCF6SFN23SG7AX66UQLS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRMXBJGCF6SFN23SG7AX66UQLS/action/storage_attestation","attest_author":"https://pith.science/pith/IRMXBJGCF6SFN23SG7AX66UQLS/action/author_attestation","sign_citation":"https://pith.science/pith/IRMXBJGCF6SFN23SG7AX66UQLS/action/citation_signature","submit_replication":"https://pith.science/pith/IRMXBJGCF6SFN23SG7AX66UQLS/action/replication_record"}},"created_at":"2026-07-05T03:53:49.952321+00:00","updated_at":"2026-07-05T03:53:49.952321+00:00"}