{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BZ2HM5DRYUPEMRNMNBGW5XKZQW","short_pith_number":"pith:BZ2HM5DR","schema_version":"1.0","canonical_sha256":"0e74767471c51e4645ac684d6edd5985af44c27941379455eea7f084928b4548","source":{"kind":"arxiv","id":"2411.17201","version":1},"attestation_state":"computed","paper":{"title":"Learning Hierarchical Polynomials of Multiple Nonlinear Features with Three-Layer Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Eshaan Nichani, Hengyu Fu, Jason D. Lee, Zihao Wang","submitted_at":"2024-11-26T08:14:48Z","abstract_excerpt":"In deep learning theory, a critical question is to understand how neural networks learn hierarchical features. In this work, we study the learning of hierarchical polynomials of \\textit{multiple nonlinear features} using three-layer neural networks. We examine a broad class of functions of the form $f^{\\star}=g^{\\star}\\circ \\bp$, where $\\bp:\\mathbb{R}^{d} \\rightarrow \\mathbb{R}^{r}$ represents multiple quadratic features with $r \\ll d$ and $g^{\\star}:\\mathbb{R}^{r}\\rightarrow \\mathbb{R}$ is a polynomial of degree $p$. This can be viewed as a nonlinear generalization of the multi-index model \\c"},"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":"2411.17201","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-26T08:14:48Z","cross_cats_sorted":["cs.AI","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"d3ff6a1e1e5ee30e9b0031b661afb5faaacf1d578113578c8844d82ffe18ce2e","abstract_canon_sha256":"0ca3eb66bbff63949f1e2967a83c1fe4edde3914f535360a2ae13017c7cfe3c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:28.967809Z","signature_b64":"jYlm/bfk///hpvdA5Cq6h+/yuOwT4ySMNnsOCudO8XYgOD2I3PyrnMdM+LJixWXyGjyfoINVlCX4x1+jnDYkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e74767471c51e4645ac684d6edd5985af44c27941379455eea7f084928b4548","last_reissued_at":"2026-07-05T09:40:28.967255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:28.967255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Hierarchical Polynomials of Multiple Nonlinear Features with Three-Layer Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Eshaan Nichani, Hengyu Fu, Jason D. Lee, Zihao Wang","submitted_at":"2024-11-26T08:14:48Z","abstract_excerpt":"In deep learning theory, a critical question is to understand how neural networks learn hierarchical features. In this work, we study the learning of hierarchical polynomials of \\textit{multiple nonlinear features} using three-layer neural networks. We examine a broad class of functions of the form $f^{\\star}=g^{\\star}\\circ \\bp$, where $\\bp:\\mathbb{R}^{d} \\rightarrow \\mathbb{R}^{r}$ represents multiple quadratic features with $r \\ll d$ and $g^{\\star}:\\mathbb{R}^{r}\\rightarrow \\mathbb{R}$ is a polynomial of degree $p$. This can be viewed as a nonlinear generalization of the multi-index model \\c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17201","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.17201/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":"2411.17201","created_at":"2026-07-05T09:40:28.967323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17201v1","created_at":"2026-07-05T09:40:28.967323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17201","created_at":"2026-07-05T09:40:28.967323+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZ2HM5DRYUPE","created_at":"2026-07-05T09:40:28.967323+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZ2HM5DRYUPEMRNM","created_at":"2026-07-05T09:40:28.967323+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZ2HM5DR","created_at":"2026-07-05T09:40:28.967323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.01763","citing_title":"On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BZ2HM5DRYUPEMRNMNBGW5XKZQW","json":"https://pith.science/pith/BZ2HM5DRYUPEMRNMNBGW5XKZQW.json","graph_json":"https://pith.science/api/pith-number/BZ2HM5DRYUPEMRNMNBGW5XKZQW/graph.json","events_json":"https://pith.science/api/pith-number/BZ2HM5DRYUPEMRNMNBGW5XKZQW/events.json","paper":"https://pith.science/paper/BZ2HM5DR"},"agent_actions":{"view_html":"https://pith.science/pith/BZ2HM5DRYUPEMRNMNBGW5XKZQW","download_json":"https://pith.science/pith/BZ2HM5DRYUPEMRNMNBGW5XKZQW.json","view_paper":"https://pith.science/paper/BZ2HM5DR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17201&json=true","fetch_graph":"https://pith.science/api/pith-number/BZ2HM5DRYUPEMRNMNBGW5XKZQW/graph.json","fetch_events":"https://pith.science/api/pith-number/BZ2HM5DRYUPEMRNMNBGW5XKZQW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZ2HM5DRYUPEMRNMNBGW5XKZQW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZ2HM5DRYUPEMRNMNBGW5XKZQW/action/storage_attestation","attest_author":"https://pith.science/pith/BZ2HM5DRYUPEMRNMNBGW5XKZQW/action/author_attestation","sign_citation":"https://pith.science/pith/BZ2HM5DRYUPEMRNMNBGW5XKZQW/action/citation_signature","submit_replication":"https://pith.science/pith/BZ2HM5DRYUPEMRNMNBGW5XKZQW/action/replication_record"}},"created_at":"2026-07-05T09:40:28.967323+00:00","updated_at":"2026-07-05T09:40:28.967323+00:00"}