{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TUPZPV2KBLTIL32ZZ3F4H66VCA","short_pith_number":"pith:TUPZPV2K","schema_version":"1.0","canonical_sha256":"9d1f97d74a0ae685ef59cecbc3fbd5103b3383a5f4f35492526625fabdba333d","source":{"kind":"arxiv","id":"2401.02592","version":3},"attestation_state":"computed","paper":{"title":"Guaranteed Nonconvex Factorization Approach for Tensor Train Recovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.SP","math.OC"],"primary_cat":"stat.ML","authors_text":"Michael B. Wakin, Zhen Qin, Zhihui Zhu","submitted_at":"2024-01-05T01:17:16Z","abstract_excerpt":"In this paper, we provide the first convergence guarantee for the factorization approach. Specifically, to avoid the scaling ambiguity and to facilitate theoretical analysis, we optimize over the so-called left-orthogonal TT format which enforces orthonormality among most of the factors. To ensure the orthonormal structure, we utilize the Riemannian gradient descent (RGD) for optimizing those factors over the Stiefel manifold. We first delve into the TT factorization problem and establish the local linear convergence of RGD. Notably, the rate of convergence only experiences a linear decline as"},"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":"2401.02592","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-01-05T01:17:16Z","cross_cats_sorted":["cs.LG","eess.SP","math.OC"],"title_canon_sha256":"b8892a303b66189b70c22e900ff198408a2690ffa04c1e09c7817bc58499c11a","abstract_canon_sha256":"05f6ef0150f5c2f6161d8887590c78684119b6abc79542a441a2a3c1883e1a15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:17.706587Z","signature_b64":"ftv6J+KmTo2vpHgk+f1WGjKpyDwtBgCh4uiJ4wdBrb6WcPkgKI1AV28TDE2yJVLeT902NOuc4fPkJQqemqMgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d1f97d74a0ae685ef59cecbc3fbd5103b3383a5f4f35492526625fabdba333d","last_reissued_at":"2026-07-05T12:01:17.706049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:17.706049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guaranteed Nonconvex Factorization Approach for Tensor Train Recovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.SP","math.OC"],"primary_cat":"stat.ML","authors_text":"Michael B. Wakin, Zhen Qin, Zhihui Zhu","submitted_at":"2024-01-05T01:17:16Z","abstract_excerpt":"In this paper, we provide the first convergence guarantee for the factorization approach. Specifically, to avoid the scaling ambiguity and to facilitate theoretical analysis, we optimize over the so-called left-orthogonal TT format which enforces orthonormality among most of the factors. To ensure the orthonormal structure, we utilize the Riemannian gradient descent (RGD) for optimizing those factors over the Stiefel manifold. We first delve into the TT factorization problem and establish the local linear convergence of RGD. Notably, the rate of convergence only experiences a linear decline as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02592","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/2401.02592/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":"2401.02592","created_at":"2026-07-05T12:01:17.706125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02592v3","created_at":"2026-07-05T12:01:17.706125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02592","created_at":"2026-07-05T12:01:17.706125+00:00"},{"alias_kind":"pith_short_12","alias_value":"TUPZPV2KBLTI","created_at":"2026-07-05T12:01:17.706125+00:00"},{"alias_kind":"pith_short_16","alias_value":"TUPZPV2KBLTIL32Z","created_at":"2026-07-05T12:01:17.706125+00:00"},{"alias_kind":"pith_short_8","alias_value":"TUPZPV2K","created_at":"2026-07-05T12:01:17.706125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.03144","citing_title":"Enhancing Quantum State Reconstruction with Structured Classical Shadows","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TUPZPV2KBLTIL32ZZ3F4H66VCA","json":"https://pith.science/pith/TUPZPV2KBLTIL32ZZ3F4H66VCA.json","graph_json":"https://pith.science/api/pith-number/TUPZPV2KBLTIL32ZZ3F4H66VCA/graph.json","events_json":"https://pith.science/api/pith-number/TUPZPV2KBLTIL32ZZ3F4H66VCA/events.json","paper":"https://pith.science/paper/TUPZPV2K"},"agent_actions":{"view_html":"https://pith.science/pith/TUPZPV2KBLTIL32ZZ3F4H66VCA","download_json":"https://pith.science/pith/TUPZPV2KBLTIL32ZZ3F4H66VCA.json","view_paper":"https://pith.science/paper/TUPZPV2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02592&json=true","fetch_graph":"https://pith.science/api/pith-number/TUPZPV2KBLTIL32ZZ3F4H66VCA/graph.json","fetch_events":"https://pith.science/api/pith-number/TUPZPV2KBLTIL32ZZ3F4H66VCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TUPZPV2KBLTIL32ZZ3F4H66VCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TUPZPV2KBLTIL32ZZ3F4H66VCA/action/storage_attestation","attest_author":"https://pith.science/pith/TUPZPV2KBLTIL32ZZ3F4H66VCA/action/author_attestation","sign_citation":"https://pith.science/pith/TUPZPV2KBLTIL32ZZ3F4H66VCA/action/citation_signature","submit_replication":"https://pith.science/pith/TUPZPV2KBLTIL32ZZ3F4H66VCA/action/replication_record"}},"created_at":"2026-07-05T12:01:17.706125+00:00","updated_at":"2026-07-05T12:01:17.706125+00:00"}