{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P2GIAUCSAT6JB2B6INIPZINWYP","short_pith_number":"pith:P2GIAUCS","schema_version":"1.0","canonical_sha256":"7e8c80505204fc90e83e4350fca1b6c3d859d8598dd54e81ceb44d5441fd3f5a","source":{"kind":"arxiv","id":"2503.20505","version":2},"attestation_state":"computed","paper":{"title":"Riemannian Optimization on Relaxed Indicator Matrix Manifold","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fangyuan Xie, Feiping Nie, Jinghui Yuan, Xuelong Li","submitted_at":"2025-03-26T12:45:52Z","abstract_excerpt":"The indicator matrix plays an important role in machine learning, but optimizing it is an NP-hard problem. We propose a new relaxation of the indicator matrix and prove that this relaxation forms a manifold, which we call the Relaxed Indicator Matrix Manifold (RIM manifold). Based on Riemannian geometry, we develop a Riemannian toolbox for optimization on the RIM manifold. Specifically, we provide several methods of Retraction, including a fast Retraction method to obtain geodesics. We point out that the RIM manifold is a generalization of the double stochastic manifold, and it is much faster "},"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":"2503.20505","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-26T12:45:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"140eb42263867dd7872e6e4d6ae399974f1f5981b33582e201a7880d6dc297e0","abstract_canon_sha256":"5e2175cbdaa6e4c5c38c5e638fbc4bd63d8d58f9db0206fc2f6167c0df926e37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:37.222864Z","signature_b64":"XyyJuK0cKZRpCLxIgWYdYpUklQt6RR4zhNyHz8ltDn5Gt6xDLXfSYmq72Pjv1C4Lilm9DlbnnAMd1FNDwWKKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e8c80505204fc90e83e4350fca1b6c3d859d8598dd54e81ceb44d5441fd3f5a","last_reissued_at":"2026-07-05T10:47:37.222396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:37.222396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Riemannian Optimization on Relaxed Indicator Matrix Manifold","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fangyuan Xie, Feiping Nie, Jinghui Yuan, Xuelong Li","submitted_at":"2025-03-26T12:45:52Z","abstract_excerpt":"The indicator matrix plays an important role in machine learning, but optimizing it is an NP-hard problem. We propose a new relaxation of the indicator matrix and prove that this relaxation forms a manifold, which we call the Relaxed Indicator Matrix Manifold (RIM manifold). Based on Riemannian geometry, we develop a Riemannian toolbox for optimization on the RIM manifold. Specifically, we provide several methods of Retraction, including a fast Retraction method to obtain geodesics. We point out that the RIM manifold is a generalization of the double stochastic manifold, and it is much faster "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20505","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.20505/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":"2503.20505","created_at":"2026-07-05T10:47:37.222453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.20505v2","created_at":"2026-07-05T10:47:37.222453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20505","created_at":"2026-07-05T10:47:37.222453+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2GIAUCSAT6J","created_at":"2026-07-05T10:47:37.222453+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2GIAUCSAT6JB2B6","created_at":"2026-07-05T10:47:37.222453+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2GIAUCS","created_at":"2026-07-05T10:47:37.222453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19351","citing_title":"DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2GIAUCSAT6JB2B6INIPZINWYP","json":"https://pith.science/pith/P2GIAUCSAT6JB2B6INIPZINWYP.json","graph_json":"https://pith.science/api/pith-number/P2GIAUCSAT6JB2B6INIPZINWYP/graph.json","events_json":"https://pith.science/api/pith-number/P2GIAUCSAT6JB2B6INIPZINWYP/events.json","paper":"https://pith.science/paper/P2GIAUCS"},"agent_actions":{"view_html":"https://pith.science/pith/P2GIAUCSAT6JB2B6INIPZINWYP","download_json":"https://pith.science/pith/P2GIAUCSAT6JB2B6INIPZINWYP.json","view_paper":"https://pith.science/paper/P2GIAUCS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.20505&json=true","fetch_graph":"https://pith.science/api/pith-number/P2GIAUCSAT6JB2B6INIPZINWYP/graph.json","fetch_events":"https://pith.science/api/pith-number/P2GIAUCSAT6JB2B6INIPZINWYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2GIAUCSAT6JB2B6INIPZINWYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2GIAUCSAT6JB2B6INIPZINWYP/action/storage_attestation","attest_author":"https://pith.science/pith/P2GIAUCSAT6JB2B6INIPZINWYP/action/author_attestation","sign_citation":"https://pith.science/pith/P2GIAUCSAT6JB2B6INIPZINWYP/action/citation_signature","submit_replication":"https://pith.science/pith/P2GIAUCSAT6JB2B6INIPZINWYP/action/replication_record"}},"created_at":"2026-07-05T10:47:37.222453+00:00","updated_at":"2026-07-05T10:47:37.222453+00:00"}