{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B4KFPYMV2NE4Z7OSWACUYQJIAV","short_pith_number":"pith:B4KFPYMV","schema_version":"1.0","canonical_sha256":"0f1457e195d349ccfdd2b0054c41280557ee00e09f1e85827f225844d2b9380f","source":{"kind":"arxiv","id":"2411.14288","version":2},"attestation_state":"computed","paper":{"title":"On the Sample Complexity of One Hidden Layer Networks with Equivariance, Locality and Weight Sharing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Arash Behboodi, Gabriele Cesa","submitted_at":"2024-11-21T16:36:01Z","abstract_excerpt":"Weight sharing, equivariance, and local filters, as in convolutional neural networks, are believed to contribute to the sample efficiency of neural networks. However, it is not clear how each one of these design choices contributes to the generalization error. Through the lens of statistical learning theory, we aim to provide insight into this question by characterizing the relative impact of each choice on the sample complexity. We obtain lower and upper sample complexity bounds for a class of single hidden layer networks. For a large class of activation functions, the bounds depend merely on"},"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":"2411.14288","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T16:36:01Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"840230c444da7e17b877962e571149a1544e306fee74c42ba4bc60cc26fe042b","abstract_canon_sha256":"51a9221a69bc7cc18a306f3884307e90803b911112324b8e478b79072d6cffce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:41.038166Z","signature_b64":"eNnH8hyHcIpZ/hIubu5Aax8J7SCh6WyIASlZdSKnKCR9livS9ukRmdbTodVrO21RlviaMq82NTwpvzKP3wJABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f1457e195d349ccfdd2b0054c41280557ee00e09f1e85827f225844d2b9380f","last_reissued_at":"2026-07-05T10:04:41.037780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:41.037780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Sample Complexity of One Hidden Layer Networks with Equivariance, Locality and Weight Sharing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Arash Behboodi, Gabriele Cesa","submitted_at":"2024-11-21T16:36:01Z","abstract_excerpt":"Weight sharing, equivariance, and local filters, as in convolutional neural networks, are believed to contribute to the sample efficiency of neural networks. However, it is not clear how each one of these design choices contributes to the generalization error. Through the lens of statistical learning theory, we aim to provide insight into this question by characterizing the relative impact of each choice on the sample complexity. We obtain lower and upper sample complexity bounds for a class of single hidden layer networks. For a large class of activation functions, the bounds depend merely on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14288","kind":"arxiv","version":2},"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/2411.14288/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":"2411.14288","created_at":"2026-07-05T10:04:41.037833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14288v2","created_at":"2026-07-05T10:04:41.037833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14288","created_at":"2026-07-05T10:04:41.037833+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4KFPYMV2NE4","created_at":"2026-07-05T10:04:41.037833+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4KFPYMV2NE4Z7OS","created_at":"2026-07-05T10:04:41.037833+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4KFPYMV","created_at":"2026-07-05T10:04:41.037833+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/B4KFPYMV2NE4Z7OSWACUYQJIAV","json":"https://pith.science/pith/B4KFPYMV2NE4Z7OSWACUYQJIAV.json","graph_json":"https://pith.science/api/pith-number/B4KFPYMV2NE4Z7OSWACUYQJIAV/graph.json","events_json":"https://pith.science/api/pith-number/B4KFPYMV2NE4Z7OSWACUYQJIAV/events.json","paper":"https://pith.science/paper/B4KFPYMV"},"agent_actions":{"view_html":"https://pith.science/pith/B4KFPYMV2NE4Z7OSWACUYQJIAV","download_json":"https://pith.science/pith/B4KFPYMV2NE4Z7OSWACUYQJIAV.json","view_paper":"https://pith.science/paper/B4KFPYMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14288&json=true","fetch_graph":"https://pith.science/api/pith-number/B4KFPYMV2NE4Z7OSWACUYQJIAV/graph.json","fetch_events":"https://pith.science/api/pith-number/B4KFPYMV2NE4Z7OSWACUYQJIAV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4KFPYMV2NE4Z7OSWACUYQJIAV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4KFPYMV2NE4Z7OSWACUYQJIAV/action/storage_attestation","attest_author":"https://pith.science/pith/B4KFPYMV2NE4Z7OSWACUYQJIAV/action/author_attestation","sign_citation":"https://pith.science/pith/B4KFPYMV2NE4Z7OSWACUYQJIAV/action/citation_signature","submit_replication":"https://pith.science/pith/B4KFPYMV2NE4Z7OSWACUYQJIAV/action/replication_record"}},"created_at":"2026-07-05T10:04:41.037833+00:00","updated_at":"2026-07-05T10:04:41.037833+00:00"}