{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CU4G7GHSGWO2N7D6UEZP3WBUW4","short_pith_number":"pith:CU4G7GHS","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"},"canonical_sha256":"15386f98f2359da6fc7ea132fdd834b7309b990896fe37a01e71fa5151b2151b","source":{"kind":"arxiv","id":"2112.07628","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07628","created_at":"2026-07-05T07:15:43Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07628v2","created_at":"2026-07-05T07:15:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07628","created_at":"2026-07-05T07:15:43Z"},{"alias_kind":"pith_short_12","alias_value":"CU4G7GHSGWO2","created_at":"2026-07-05T07:15:43Z"},{"alias_kind":"pith_short_16","alias_value":"CU4G7GHSGWO2N7D6","created_at":"2026-07-05T07:15:43Z"},{"alias_kind":"pith_short_8","alias_value":"CU4G7GHS","created_at":"2026-07-05T07:15:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CU4G7GHSGWO2N7D6UEZP3WBUW4","target":"record","payload":{"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"},"canonical_sha256":"15386f98f2359da6fc7ea132fdd834b7309b990896fe37a01e71fa5151b2151b","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"},"source_kind":"arxiv","source_id":"2112.07628","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:15:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"27AhXGCIjqWr+ZXRmUwqqpw9QSFsFWVyT8ScS4Pc5QGQrjv1x/YUnKF0jg7vjiA/abrff6DmoAfyHv0grQE8Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:59:58.311018Z"},"content_sha256":"f610827a3a9b3b0bbc30f8b50725642f9c4d0bbc3afd79d13a593c69534847a4","schema_version":"1.0","event_id":"sha256:f610827a3a9b3b0bbc30f8b50725642f9c4d0bbc3afd79d13a593c69534847a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CU4G7GHSGWO2N7D6UEZP3WBUW4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:15:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g1V5lWe3i2oq5On6GCqd8V3aWR25YygIvMX7NUoR2BviXNN2Dwp4TM2AReCsDec7+q3Xzpu/9mHt4ncAs/u5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:59:58.311421Z"},"content_sha256":"d041d09765fa9e482fd1098a6eb51a4f85960684d673b58725d8b0725e109603","schema_version":"1.0","event_id":"sha256:d041d09765fa9e482fd1098a6eb51a4f85960684d673b58725d8b0725e109603"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CU4G7GHSGWO2N7D6UEZP3WBUW4/bundle.json","state_url":"https://pith.science/pith/CU4G7GHSGWO2N7D6UEZP3WBUW4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CU4G7GHSGWO2N7D6UEZP3WBUW4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T19:59:58Z","links":{"resolver":"https://pith.science/pith/CU4G7GHSGWO2N7D6UEZP3WBUW4","bundle":"https://pith.science/pith/CU4G7GHSGWO2N7D6UEZP3WBUW4/bundle.json","state":"https://pith.science/pith/CU4G7GHSGWO2N7D6UEZP3WBUW4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CU4G7GHSGWO2N7D6UEZP3WBUW4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CU4G7GHSGWO2N7D6UEZP3WBUW4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"52c74f6cce12eb3bc65006428a4a14365941edb5896e79d919fd4ac78473a371","cross_cats_sorted":["cs.DS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T18:13:36Z","title_canon_sha256":"e927efc2968bf22551b9ccdd62a7c885fd7f788c4e1b315e0392f6319d4cbdb2"},"schema_version":"1.0","source":{"id":"2112.07628","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07628","created_at":"2026-07-05T07:15:43Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07628v2","created_at":"2026-07-05T07:15:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07628","created_at":"2026-07-05T07:15:43Z"},{"alias_kind":"pith_short_12","alias_value":"CU4G7GHSGWO2","created_at":"2026-07-05T07:15:43Z"},{"alias_kind":"pith_short_16","alias_value":"CU4G7GHSGWO2N7D6","created_at":"2026-07-05T07:15:43Z"},{"alias_kind":"pith_short_8","alias_value":"CU4G7GHS","created_at":"2026-07-05T07:15:43Z"}],"graph_snapshots":[{"event_id":"sha256:d041d09765fa9e482fd1098a6eb51a4f85960684d673b58725d8b0725e109603","target":"graph","created_at":"2026-07-05T07:15:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.07628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lichen Zhang, Ruizhe Zhang, Zhao Song","cross_cats":["cs.DS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T18:13:36Z","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07628","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f610827a3a9b3b0bbc30f8b50725642f9c4d0bbc3afd79d13a593c69534847a4","target":"record","created_at":"2026-07-05T07:15:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"52c74f6cce12eb3bc65006428a4a14365941edb5896e79d919fd4ac78473a371","cross_cats_sorted":["cs.DS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T18:13:36Z","title_canon_sha256":"e927efc2968bf22551b9ccdd62a7c885fd7f788c4e1b315e0392f6319d4cbdb2"},"schema_version":"1.0","source":{"id":"2112.07628","kind":"arxiv","version":2}},"canonical_sha256":"15386f98f2359da6fc7ea132fdd834b7309b990896fe37a01e71fa5151b2151b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15386f98f2359da6fc7ea132fdd834b7309b990896fe37a01e71fa5151b2151b","first_computed_at":"2026-07-05T07:15:43.158770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:15:43.158770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F2/TNTc+hT2Zi8TzRwkg/ZLnxKUKn/S51orrYeHl1NKmY6l8wt1qoA5j1voEExuNqeQzIG97SSIB7XAjxFFrCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:15:43.159206Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.07628","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f610827a3a9b3b0bbc30f8b50725642f9c4d0bbc3afd79d13a593c69534847a4","sha256:d041d09765fa9e482fd1098a6eb51a4f85960684d673b58725d8b0725e109603"],"state_sha256":"29160a84858bcd17b29d90de43508cf404392a9ac843e9d7bbbd36678ee576ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vxIQr/ETMzeqxbmf2Rrdvl2GyE5pE4/Akj2josdNlX7+lITsTdLgiEmIYfN+2bki0Tx3x1feJtU1g7LTDyekBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T19:59:58.313561Z","bundle_sha256":"718c1cf50e7271f052fcba3a8380f069a4fe63b07fc7acc6d7505c940973c6e9"}}