{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IIJHBX4UV4MXIVSAWBQMYR3VQX","short_pith_number":"pith:IIJHBX4U","schema_version":"1.0","canonical_sha256":"421270df94af19745640b060cc477585fa785efccdd107b529df3e8773f8cb22","source":{"kind":"arxiv","id":"1901.02975","version":1},"attestation_state":"computed","paper":{"title":"A witness function based construction of discriminative models using Hermite polynomials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"A. Cloninger, H. N. Mhaskar, X. Cheng","submitted_at":"2019-01-10T00:14:26Z","abstract_excerpt":"In machine learning, we are given a dataset of the form $\\{(\\mathbf{x}_j,y_j)\\}_{j=1}^M$, drawn as i.i.d. samples from an unknown probability distribution $\\mu$; the marginal distribution for the $\\mathbf{x}_j$'s being $\\mu^*$. We propose that rather than using a positive kernel such as the Gaussian for estimation of these measures, using a non-positive kernel that preserves a large number of moments of these measures yields an optimal approximation. We use multi-variate Hermite polynomials for this purpose, and prove optimal and local approximation results in a supremum norm in a probabilisti"},"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":"1901.02975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-10T00:14:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b7156584b32ef2cf40cd8f2ba51869167317b76b656ef06599fda916c746cc6d","abstract_canon_sha256":"60e493ccf0f7b74f938dbe6acadaa79e56fb70badf8b8065104b4a890c3db1e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:35.887885Z","signature_b64":"v4EzfQr/z8tYBFYwuDiOLGXwNcHDgUIG+xnzL825BfzpKqSUBwv+vItif3nhOW51BM216dP0LYdfr9Mz9fffDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"421270df94af19745640b060cc477585fa785efccdd107b529df3e8773f8cb22","last_reissued_at":"2026-05-17T23:56:35.887433Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:35.887433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A witness function based construction of discriminative models using Hermite polynomials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"A. Cloninger, H. N. Mhaskar, X. Cheng","submitted_at":"2019-01-10T00:14:26Z","abstract_excerpt":"In machine learning, we are given a dataset of the form $\\{(\\mathbf{x}_j,y_j)\\}_{j=1}^M$, drawn as i.i.d. samples from an unknown probability distribution $\\mu$; the marginal distribution for the $\\mathbf{x}_j$'s being $\\mu^*$. We propose that rather than using a positive kernel such as the Gaussian for estimation of these measures, using a non-positive kernel that preserves a large number of moments of these measures yields an optimal approximation. We use multi-variate Hermite polynomials for this purpose, and prove optimal and local approximation results in a supremum norm in a probabilisti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02975","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":"1901.02975","created_at":"2026-05-17T23:56:35.887497+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.02975v1","created_at":"2026-05-17T23:56:35.887497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02975","created_at":"2026-05-17T23:56:35.887497+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIJHBX4UV4MX","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIJHBX4UV4MXIVSA","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIJHBX4U","created_at":"2026-05-18T12:33:18.533446+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/IIJHBX4UV4MXIVSAWBQMYR3VQX","json":"https://pith.science/pith/IIJHBX4UV4MXIVSAWBQMYR3VQX.json","graph_json":"https://pith.science/api/pith-number/IIJHBX4UV4MXIVSAWBQMYR3VQX/graph.json","events_json":"https://pith.science/api/pith-number/IIJHBX4UV4MXIVSAWBQMYR3VQX/events.json","paper":"https://pith.science/paper/IIJHBX4U"},"agent_actions":{"view_html":"https://pith.science/pith/IIJHBX4UV4MXIVSAWBQMYR3VQX","download_json":"https://pith.science/pith/IIJHBX4UV4MXIVSAWBQMYR3VQX.json","view_paper":"https://pith.science/paper/IIJHBX4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.02975&json=true","fetch_graph":"https://pith.science/api/pith-number/IIJHBX4UV4MXIVSAWBQMYR3VQX/graph.json","fetch_events":"https://pith.science/api/pith-number/IIJHBX4UV4MXIVSAWBQMYR3VQX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIJHBX4UV4MXIVSAWBQMYR3VQX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIJHBX4UV4MXIVSAWBQMYR3VQX/action/storage_attestation","attest_author":"https://pith.science/pith/IIJHBX4UV4MXIVSAWBQMYR3VQX/action/author_attestation","sign_citation":"https://pith.science/pith/IIJHBX4UV4MXIVSAWBQMYR3VQX/action/citation_signature","submit_replication":"https://pith.science/pith/IIJHBX4UV4MXIVSAWBQMYR3VQX/action/replication_record"}},"created_at":"2026-05-17T23:56:35.887497+00:00","updated_at":"2026-05-17T23:56:35.887497+00:00"}