{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P4T6BU2ABWCFZLLFZ4OTHEAEXG","short_pith_number":"pith:P4T6BU2A","schema_version":"1.0","canonical_sha256":"7f27e0d3400d845cad65cf1d339004b9a8c1bce81500629a96140f0374f4b41a","source":{"kind":"arxiv","id":"2506.05500","version":1},"attestation_state":"computed","paper":{"title":"The Generative Leap: Sharp Sample Complexity for Efficiently Learning Gaussian Multi-Index Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Damian, Jason D. Lee, Joan Bruna","submitted_at":"2025-06-05T18:34:56Z","abstract_excerpt":"In this work we consider generic Gaussian Multi-index models, in which the labels only depend on the (Gaussian) $d$-dimensional inputs through their projection onto a low-dimensional $r = O_d(1)$ subspace, and we study efficient agnostic estimation procedures for this hidden subspace. We introduce the \\emph{generative leap} exponent $k^\\star$, a natural extension of the generative exponent from [Damian et al.'24] to the multi-index setting. We first show that a sample complexity of $n=\\Theta(d^{1 \\vee \\k/2})$ is necessary in the class of algorithms captured by the Low-Degree-Polynomial framewo"},"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":"2506.05500","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T18:34:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"02f3f0e4335b47925c72c4efe5386f1d4256c74be4aad2ffba11b3750e33dfb7","abstract_canon_sha256":"92a0ce072fd4eb8c33b00c3c5fbe9344c1beb555a1f0268e2f5bd910756dca96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:03.836100Z","signature_b64":"RMJ0nNia8EwvJqbPVPo7P/wXKcxbAY9A+pETMWDWped5ugvxzVVLm+noF8umxCgptOIF4j2x/xzoNpISsB6dDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f27e0d3400d845cad65cf1d339004b9a8c1bce81500629a96140f0374f4b41a","last_reissued_at":"2026-07-05T11:17:03.834908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:03.834908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Generative Leap: Sharp Sample Complexity for Efficiently Learning Gaussian Multi-Index Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Damian, Jason D. Lee, Joan Bruna","submitted_at":"2025-06-05T18:34:56Z","abstract_excerpt":"In this work we consider generic Gaussian Multi-index models, in which the labels only depend on the (Gaussian) $d$-dimensional inputs through their projection onto a low-dimensional $r = O_d(1)$ subspace, and we study efficient agnostic estimation procedures for this hidden subspace. We introduce the \\emph{generative leap} exponent $k^\\star$, a natural extension of the generative exponent from [Damian et al.'24] to the multi-index setting. We first show that a sample complexity of $n=\\Theta(d^{1 \\vee \\k/2})$ is necessary in the class of algorithms captured by the Low-Degree-Polynomial framewo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05500","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/2506.05500/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":"2506.05500","created_at":"2026-07-05T11:17:03.835574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05500v1","created_at":"2026-07-05T11:17:03.835574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05500","created_at":"2026-07-05T11:17:03.835574+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4T6BU2ABWCF","created_at":"2026-07-05T11:17:03.835574+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4T6BU2ABWCFZLLF","created_at":"2026-07-05T11:17:03.835574+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4T6BU2A","created_at":"2026-07-05T11:17:03.835574+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/P4T6BU2ABWCFZLLFZ4OTHEAEXG","json":"https://pith.science/pith/P4T6BU2ABWCFZLLFZ4OTHEAEXG.json","graph_json":"https://pith.science/api/pith-number/P4T6BU2ABWCFZLLFZ4OTHEAEXG/graph.json","events_json":"https://pith.science/api/pith-number/P4T6BU2ABWCFZLLFZ4OTHEAEXG/events.json","paper":"https://pith.science/paper/P4T6BU2A"},"agent_actions":{"view_html":"https://pith.science/pith/P4T6BU2ABWCFZLLFZ4OTHEAEXG","download_json":"https://pith.science/pith/P4T6BU2ABWCFZLLFZ4OTHEAEXG.json","view_paper":"https://pith.science/paper/P4T6BU2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05500&json=true","fetch_graph":"https://pith.science/api/pith-number/P4T6BU2ABWCFZLLFZ4OTHEAEXG/graph.json","fetch_events":"https://pith.science/api/pith-number/P4T6BU2ABWCFZLLFZ4OTHEAEXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4T6BU2ABWCFZLLFZ4OTHEAEXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4T6BU2ABWCFZLLFZ4OTHEAEXG/action/storage_attestation","attest_author":"https://pith.science/pith/P4T6BU2ABWCFZLLFZ4OTHEAEXG/action/author_attestation","sign_citation":"https://pith.science/pith/P4T6BU2ABWCFZLLFZ4OTHEAEXG/action/citation_signature","submit_replication":"https://pith.science/pith/P4T6BU2ABWCFZLLFZ4OTHEAEXG/action/replication_record"}},"created_at":"2026-07-05T11:17:03.835574+00:00","updated_at":"2026-07-05T11:17:03.835574+00:00"}