{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XERIYRSD4HGXFZLMDGOL3VMDDW","short_pith_number":"pith:XERIYRSD","schema_version":"1.0","canonical_sha256":"b9228c4643e1cd72e56c199cbdd5831dab337f4296f3293e5cc22b8ce835e57f","source":{"kind":"arxiv","id":"1906.08899","version":1},"attestation_state":"computed","paper":{"title":"Limitations of Lazy Training of Two-layers Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Andrea Montanari, Behrooz Ghorbani, Song Mei, Theodor Misiakiewicz","submitted_at":"2019-06-21T00:29:54Z","abstract_excerpt":"We study the supervised learning problem under either of the following two models: (1) Feature vectors ${\\boldsymbol x}_i$ are $d$-dimensional Gaussians and responses are $y_i = f_*({\\boldsymbol x}_i)$ for $f_*$ an unknown quadratic function; (2) Feature vectors ${\\boldsymbol x}_i$ are distributed as a mixture of two $d$-dimensional centered Gaussians, and $y_i$'s are the corresponding class labels. We use two-layers neural networks with quadratic activations, and compare three different learning regimes: the random features (RF) regime in which we only train the second-layer weights; the neur"},"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":"1906.08899","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-21T00:29:54Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"3d2f8609b2bad0ecf331eb92e93bfcde3d92b845323f47a010bcb4f482f9480c","abstract_canon_sha256":"31778cf7f8c00f5293f0830e12d8b0aaff476108ab5615a55230c9550b2a88e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:47.485141Z","signature_b64":"mt1CTHDOog4oBFgNgsF3ELQ9M28yubrP9alHw/blpaa6wkqAEhwfm6n9x0xxyv8YzReAZZuhq1Rj6myuKVCRAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9228c4643e1cd72e56c199cbdd5831dab337f4296f3293e5cc22b8ce835e57f","last_reissued_at":"2026-05-17T23:42:47.484516Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:47.484516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Limitations of Lazy Training of Two-layers Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Andrea Montanari, Behrooz Ghorbani, Song Mei, Theodor Misiakiewicz","submitted_at":"2019-06-21T00:29:54Z","abstract_excerpt":"We study the supervised learning problem under either of the following two models: (1) Feature vectors ${\\boldsymbol x}_i$ are $d$-dimensional Gaussians and responses are $y_i = f_*({\\boldsymbol x}_i)$ for $f_*$ an unknown quadratic function; (2) Feature vectors ${\\boldsymbol x}_i$ are distributed as a mixture of two $d$-dimensional centered Gaussians, and $y_i$'s are the corresponding class labels. We use two-layers neural networks with quadratic activations, and compare three different learning regimes: the random features (RF) regime in which we only train the second-layer weights; the neur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08899","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1906.08899","created_at":"2026-05-17T23:42:47.484738+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.08899v1","created_at":"2026-05-17T23:42:47.484738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08899","created_at":"2026-05-17T23:42:47.484738+00:00"},{"alias_kind":"pith_short_12","alias_value":"XERIYRSD4HGX","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"XERIYRSD4HGXFZLM","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"XERIYRSD","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XERIYRSD4HGXFZLMDGOL3VMDDW","json":"https://pith.science/pith/XERIYRSD4HGXFZLMDGOL3VMDDW.json","graph_json":"https://pith.science/api/pith-number/XERIYRSD4HGXFZLMDGOL3VMDDW/graph.json","events_json":"https://pith.science/api/pith-number/XERIYRSD4HGXFZLMDGOL3VMDDW/events.json","paper":"https://pith.science/paper/XERIYRSD"},"agent_actions":{"view_html":"https://pith.science/pith/XERIYRSD4HGXFZLMDGOL3VMDDW","download_json":"https://pith.science/pith/XERIYRSD4HGXFZLMDGOL3VMDDW.json","view_paper":"https://pith.science/paper/XERIYRSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.08899&json=true","fetch_graph":"https://pith.science/api/pith-number/XERIYRSD4HGXFZLMDGOL3VMDDW/graph.json","fetch_events":"https://pith.science/api/pith-number/XERIYRSD4HGXFZLMDGOL3VMDDW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XERIYRSD4HGXFZLMDGOL3VMDDW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XERIYRSD4HGXFZLMDGOL3VMDDW/action/storage_attestation","attest_author":"https://pith.science/pith/XERIYRSD4HGXFZLMDGOL3VMDDW/action/author_attestation","sign_citation":"https://pith.science/pith/XERIYRSD4HGXFZLMDGOL3VMDDW/action/citation_signature","submit_replication":"https://pith.science/pith/XERIYRSD4HGXFZLMDGOL3VMDDW/action/replication_record"}},"created_at":"2026-05-17T23:42:47.484738+00:00","updated_at":"2026-05-17T23:42:47.484738+00:00"}