{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:N755QZ6RB3BMV2I5HBEJJIBOPM","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":"d8a6e46656d7d05a3c68f8f1c31560f9280328ca56df7fa6637bb023334df9c2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-10-22T00:32:12Z","title_canon_sha256":"ccf2392e7bd05a06eb2cd3e2ff81fc9b3dc89e1249dac12f748fa7fb2529ea90"},"schema_version":"1.0","source":{"id":"2010.11356","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.11356","created_at":"2026-07-05T01:45:09Z"},{"alias_kind":"arxiv_version","alias_value":"2010.11356v1","created_at":"2026-07-05T01:45:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11356","created_at":"2026-07-05T01:45:09Z"},{"alias_kind":"pith_short_12","alias_value":"N755QZ6RB3BM","created_at":"2026-07-05T01:45:09Z"},{"alias_kind":"pith_short_16","alias_value":"N755QZ6RB3BMV2I5","created_at":"2026-07-05T01:45:09Z"},{"alias_kind":"pith_short_8","alias_value":"N755QZ6R","created_at":"2026-07-05T01:45:09Z"}],"graph_snapshots":[{"event_id":"sha256:91463b5791370dc03246cf65f33111b94b8e6faf98c1c045c1509832ac48692e","target":"graph","created_at":"2026-07-05T01:45:09Z","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/2010.11356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Over-parametrization is an important technique in training neural networks. In both theory and practice, training a larger network allows the optimization algorithm to avoid bad local optimal solutions. In this paper we study a closely related tensor decomposition problem: given an $l$-th order tensor in $(R^d)^{\\otimes l}$ of rank $r$ (where $r\\ll d$), can variants of gradient descent find a rank $m$ decomposition where $m > r$? We show that in a lazy training regime (similar to the NTK regime for neural networks) one needs at least $m = \\Omega(d^{l-1})$, while a variant of gradient descent c","authors_text":"Chenwei Wu, Jason D. Lee, Rong Ge, Tengyu Ma, Xiang Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-10-22T00:32:12Z","title":"Beyond Lazy Training for Over-parameterized Tensor Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11356","kind":"arxiv","version":1},"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":"sha256:55d519961cc22a9c36f53132232c1ab2d569b75174f0e0491a89a8f7a9e86162","target":"record","created_at":"2026-07-05T01:45:09Z","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":"d8a6e46656d7d05a3c68f8f1c31560f9280328ca56df7fa6637bb023334df9c2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-10-22T00:32:12Z","title_canon_sha256":"ccf2392e7bd05a06eb2cd3e2ff81fc9b3dc89e1249dac12f748fa7fb2529ea90"},"schema_version":"1.0","source":{"id":"2010.11356","kind":"arxiv","version":1}},"canonical_sha256":"6ffbd867d10ec2cae91d384894a02e7b38ea03a9d89c0e79dbe468ed13485852","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ffbd867d10ec2cae91d384894a02e7b38ea03a9d89c0e79dbe468ed13485852","first_computed_at":"2026-07-05T01:45:09.126261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:09.126261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AXjZKGOQFENssE7Vb031NYkkYDQ60ezcyhoAB/Zhs09ZowhX4LTSwe5zbQKSDvZwPyHdnkfGw0NPtt9h/KzKCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:09.126707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.11356","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55d519961cc22a9c36f53132232c1ab2d569b75174f0e0491a89a8f7a9e86162","sha256:91463b5791370dc03246cf65f33111b94b8e6faf98c1c045c1509832ac48692e"],"state_sha256":"31359a751a446676fee6402c54e86b6eb3845b9c13234cb4e34223ee6eb7c17d"}