{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RPHRCEJLBY3GAW7NH2G7OJ2XDQ","short_pith_number":"pith:RPHRCEJL","schema_version":"1.0","canonical_sha256":"8bcf11112b0e36605bed3e8df727571c35cd04e23f6389a3e1f08a728a002ff2","source":{"kind":"arxiv","id":"2605.15082","version":1},"attestation_state":"computed","paper":{"title":"Average Gradient Outer Product in kernel regression provably recovers the central subspace for multi-index models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"The average gradient outer product from kernel ridge regression recovers the central subspace of multi-index models in sample regimes too small for accurate prediction.","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Damek Davis, Dmitriy Drusvyatskiy, Libin Zhu, Maryam Fazel","submitted_at":"2026-05-14T17:05:30Z","abstract_excerpt":"We study a prototypical situation when a learned predictor can discover useful low-dimensional structure in data, while using fewer samples than are needed for accurate prediction. Specifically, we consider the problem of recovering a multi-index polynomial $f^*(x)=h(Ux)$, with $U\\in\\mathbb{R}^{r\\times d}$ and $r\\ll d$, from finitely many data/label pairs. Importantly, the target function depends on input $x$ only through the projection onto an unknown $r$-dimensional central subspace. The algorithm we analyze is appealingly simple: fit kernel ridge regression (KRR) to the data and compute the"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.15082","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-14T17:05:30Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"45e919745effab06b7d8d5c9d9a01da6c72fc48e270ca2edebcc81d9bce79670","abstract_canon_sha256":"b7e660042d30ada8fb1589a6ead7239b370037ac9f2b5b5f55d84fde3c2260bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.2","canonical_sha256":"8bcf11112b0e36605bed3e8df727571c35cd04e23f6389a3e1f08a728a002ff2","last_reissued_at":"2026-05-17T21:57:19.284907Z","signature_status":"unsigned_v0","first_computed_at":"2026-05-17T21:40:25.977506Z"},"graph_snapshot":{"paper":{"title":"Average Gradient Outer Product in kernel regression provably recovers the central subspace for multi-index models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"The average gradient outer product from kernel ridge regression recovers the central subspace of multi-index models in sample regimes too small for accurate prediction.","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Damek Davis, Dmitriy Drusvyatskiy, Libin Zhu, Maryam Fazel","submitted_at":"2026-05-14T17:05:30Z","abstract_excerpt":"We study a prototypical situation when a learned predictor can discover useful low-dimensional structure in data, while using fewer samples than are needed for accurate prediction. Specifically, we consider the problem of recovering a multi-index polynomial $f^*(x)=h(Ux)$, with $U\\in\\mathbb{R}^{r\\times d}$ and $r\\ll d$, from finitely many data/label pairs. Importantly, the target function depends on input $x$ only through the projection onto an unknown $r$-dimensional central subspace. The algorithm we analyze is appealingly simple: fit kernel ridge regression (KRR) to the data and compute the"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"the top r-dimensional eigenspace of AGOP provably recovers the central subspace, even in regimes when the prediction error remains large. Specifically, if the target function f* has degree p*, ... subspace recovery occurs in the much lower sample regime n ≍ d^{p+δ} for any δ ∈ (0,1).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"a low degree p component of f* already carries all relevant directions for prediction, together with unspecified 'reasonable assumptions' on the kernel and the multi-index structure (abstract only).","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"For multi-index polynomials, the top r eigenspace of the AGOP matrix from KRR recovers the central subspace at sample complexity n ~ d^{p+δ} where p is the degree of the informative component.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The average gradient outer product from kernel ridge regression recovers the central subspace of multi-index models in sample regimes too small for accurate prediction.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"45310b90d8bc0c84b1d0a09e96c47bebf99c9878d66db731277a0f6de1693b7e"},"source":{"id":"2605.15082","kind":"arxiv","version":1},"verdict":{"id":"a08aba0c-35c9-45ae-baca-7e51e7df039e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:05:53.439476Z","strongest_claim":"the top r-dimensional eigenspace of AGOP provably recovers the central subspace, even in regimes when the prediction error remains large. Specifically, if the target function f* has degree p*, ... subspace recovery occurs in the much lower sample regime n ≍ d^{p+δ} for any δ ∈ (0,1).","one_line_summary":"For multi-index polynomials, the top r eigenspace of the AGOP matrix from KRR recovers the central subspace at sample complexity n ~ d^{p+δ} where p is the degree of the informative component.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"a low degree p component of f* already carries all relevant directions for prediction, together with unspecified 'reasonable assumptions' on the kernel and the multi-index structure (abstract only).","pith_extraction_headline":"The average gradient outer product from kernel ridge regression recovers the central subspace of multi-index models in sample regimes too small for accurate prediction."},"references":{"count":64,"sample":[{"doi":"","year":2023,"title":"Sgd learning on neural networks: leap complexity and saddle-to-saddle dynamics","work_id":"c710cb1d-e477-4ec1-91b5-a8534000fc4e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"The merged-staircase property: a necessary and nearly sufficient condition for sgd learning of sparse functions on two-layer neural networks","work_id":"4d8fa6c0-826f-4638-986c-6f3c0d96af37","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Classical orthogonal polynomials","work_id":"93ead7bf-64f0-4d79-9e77-66dbc737e138","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2006,"title":"Springer. 2006, pp. 36–62","work_id":"151a1b61-ae68-4f67-b38b-57c5462d3dea","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Online learning and information exponents: On the importance of batch size, and time/complexity tradeoffs","work_id":"0e969c0f-81e0-4313-af54-714970b4945a","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":64,"snapshot_sha256":"d40a3fedb25ffe5dd07b0cccca202bc662cdbfc53b810f036b02bd0af43a4d99","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"be6fd5681d87fd153a1276402e7e512cbf7be9cc4564aa2c216aaf765ed23e22"},"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":"2605.15082","created_at":"2026-05-17T21:18:33.519167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15082v1","created_at":"2026-05-17T21:18:33.519167+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPHRCEJLBY3G","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPHRCEJLBY3GAW7N","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPHRCEJL","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RPHRCEJLBY3GAW7NH2G7OJ2XDQ","json":"https://pith.science/pith/RPHRCEJLBY3GAW7NH2G7OJ2XDQ.json","graph_json":"https://pith.science/api/pith-number/RPHRCEJLBY3GAW7NH2G7OJ2XDQ/graph.json","events_json":"https://pith.science/api/pith-number/RPHRCEJLBY3GAW7NH2G7OJ2XDQ/events.json","paper":"https://pith.science/paper/RPHRCEJL"},"agent_actions":{"view_html":"https://pith.science/pith/RPHRCEJLBY3GAW7NH2G7OJ2XDQ","download_json":"https://pith.science/pith/RPHRCEJLBY3GAW7NH2G7OJ2XDQ.json","view_paper":"https://pith.science/paper/RPHRCEJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15082&json=true","fetch_graph":"https://pith.science/api/pith-number/RPHRCEJLBY3GAW7NH2G7OJ2XDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/RPHRCEJLBY3GAW7NH2G7OJ2XDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPHRCEJLBY3GAW7NH2G7OJ2XDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPHRCEJLBY3GAW7NH2G7OJ2XDQ/action/storage_attestation","attest_author":"https://pith.science/pith/RPHRCEJLBY3GAW7NH2G7OJ2XDQ/action/author_attestation","sign_citation":"https://pith.science/pith/RPHRCEJLBY3GAW7NH2G7OJ2XDQ/action/citation_signature","submit_replication":"https://pith.science/pith/RPHRCEJLBY3GAW7NH2G7OJ2XDQ/action/replication_record"}},"created_at":"2026-05-17T21:18:33.519167+00:00","updated_at":"2026-05-17T21:57:19.285003+00:00"}