{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CU4G7GHSGWO2N7D6UEZP3WBUW4","short_pith_number":"pith:CU4G7GHS","schema_version":"1.0","canonical_sha256":"15386f98f2359da6fc7ea132fdd834b7309b990896fe37a01e71fa5151b2151b","source":{"kind":"arxiv","id":"2112.07628","version":2},"attestation_state":"computed","paper":{"title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Lichen Zhang, Ruizhe Zhang, Zhao Song","submitted_at":"2021-12-14T18:13:36Z","abstract_excerpt":"We consider the problem of training a multi-layer over-parametrized neural network to minimize the empirical risk induced by a loss function. In the typical setting of over-parametrization, the network width $m$ is much larger than the data dimension $d$ and the number of training samples $n$ ($m=\\mathrm{poly}(n,d)$), which induces a prohibitive large weight matrix $W\\in \\mathbb{R}^{m\\times m}$ per layer. Naively, one has to pay $O(m^2)$ time to read the weight matrix and evaluate the neural network function in both forward and backward computation. In this work, we show how to reduce the trai"},"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":"2112.07628","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T18:13:36Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"e927efc2968bf22551b9ccdd62a7c885fd7f788c4e1b315e0392f6319d4cbdb2","abstract_canon_sha256":"52c74f6cce12eb3bc65006428a4a14365941edb5896e79d919fd4ac78473a371"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:43.159206Z","signature_b64":"F2/TNTc+hT2Zi8TzRwkg/ZLnxKUKn/S51orrYeHl1NKmY6l8wt1qoA5j1voEExuNqeQzIG97SSIB7XAjxFFrCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15386f98f2359da6fc7ea132fdd834b7309b990896fe37a01e71fa5151b2151b","last_reissued_at":"2026-07-05T07:15:43.158770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:43.158770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Lichen Zhang, Ruizhe Zhang, Zhao Song","submitted_at":"2021-12-14T18:13:36Z","abstract_excerpt":"We consider the problem of training a multi-layer over-parametrized neural network to minimize the empirical risk induced by a loss function. In the typical setting of over-parametrization, the network width $m$ is much larger than the data dimension $d$ and the number of training samples $n$ ($m=\\mathrm{poly}(n,d)$), which induces a prohibitive large weight matrix $W\\in \\mathbb{R}^{m\\times m}$ per layer. Naively, one has to pay $O(m^2)$ time to read the weight matrix and evaluate the neural network function in both forward and backward computation. In this work, we show how to reduce the trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07628","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/2112.07628/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":"2112.07628","created_at":"2026-07-05T07:15:43.158831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.07628v2","created_at":"2026-07-05T07:15:43.158831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07628","created_at":"2026-07-05T07:15:43.158831+00:00"},{"alias_kind":"pith_short_12","alias_value":"CU4G7GHSGWO2","created_at":"2026-07-05T07:15:43.158831+00:00"},{"alias_kind":"pith_short_16","alias_value":"CU4G7GHSGWO2N7D6","created_at":"2026-07-05T07:15:43.158831+00:00"},{"alias_kind":"pith_short_8","alias_value":"CU4G7GHS","created_at":"2026-07-05T07:15:43.158831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10933","citing_title":"DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10933","citing_title":"DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10933","citing_title":"DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices","ref_index":82,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CU4G7GHSGWO2N7D6UEZP3WBUW4","json":"https://pith.science/pith/CU4G7GHSGWO2N7D6UEZP3WBUW4.json","graph_json":"https://pith.science/api/pith-number/CU4G7GHSGWO2N7D6UEZP3WBUW4/graph.json","events_json":"https://pith.science/api/pith-number/CU4G7GHSGWO2N7D6UEZP3WBUW4/events.json","paper":"https://pith.science/paper/CU4G7GHS"},"agent_actions":{"view_html":"https://pith.science/pith/CU4G7GHSGWO2N7D6UEZP3WBUW4","download_json":"https://pith.science/pith/CU4G7GHSGWO2N7D6UEZP3WBUW4.json","view_paper":"https://pith.science/paper/CU4G7GHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.07628&json=true","fetch_graph":"https://pith.science/api/pith-number/CU4G7GHSGWO2N7D6UEZP3WBUW4/graph.json","fetch_events":"https://pith.science/api/pith-number/CU4G7GHSGWO2N7D6UEZP3WBUW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CU4G7GHSGWO2N7D6UEZP3WBUW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CU4G7GHSGWO2N7D6UEZP3WBUW4/action/storage_attestation","attest_author":"https://pith.science/pith/CU4G7GHSGWO2N7D6UEZP3WBUW4/action/author_attestation","sign_citation":"https://pith.science/pith/CU4G7GHSGWO2N7D6UEZP3WBUW4/action/citation_signature","submit_replication":"https://pith.science/pith/CU4G7GHSGWO2N7D6UEZP3WBUW4/action/replication_record"}},"created_at":"2026-07-05T07:15:43.158831+00:00","updated_at":"2026-07-05T07:15:43.158831+00:00"}