{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A4JNB3I4H773OCORTGXDJEGPQX","short_pith_number":"pith:A4JNB3I4","schema_version":"1.0","canonical_sha256":"0712d0ed1c3fffb709d199ae3490cf85fb6e4744ae9e7236d241ae0d7c5c7b80","source":{"kind":"arxiv","id":"2402.14103","version":2},"attestation_state":"computed","paper":{"title":"Computational-Statistical Gaps for Improper Learning in Sparse Linear Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Jingqiu Ding, Rares-Darius Buhai, Stefan Tiegel","submitted_at":"2024-02-21T19:55:01Z","abstract_excerpt":"We study computational-statistical gaps for improper learning in sparse linear regression. More specifically, given $n$ samples from a $k$-sparse linear model in dimension $d$, we ask what is the minimum sample complexity to efficiently (in time polynomial in $d$, $k$, and $n$) find a potentially dense estimate for the regression vector that achieves non-trivial prediction error on the $n$ samples. Information-theoretically this can be achieved using $\\Theta(k \\log (d/k))$ samples. Yet, despite its prominence in the literature, there is no polynomial-time algorithm known to achieve the same gu"},"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":"2402.14103","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T19:55:01Z","cross_cats_sorted":["cs.CC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"ed7fe5fcb02dba470f7fed41cc3aa6d6579f9fa0fe4b607f29c6fb5bd920172a","abstract_canon_sha256":"2e24c61f574fabc1da97e72d6000ca5931ede0a8d1f9793ee86e303186fa7660"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:22.902734Z","signature_b64":"7NjwOZOyFH5aBhZCPZ1ohd0D56BPLrlAeJ6pKDMCC/A0elZ7/zUiRQyPiF7JgnYg13zRKKfRCPApQsPwDUMoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0712d0ed1c3fffb709d199ae3490cf85fb6e4744ae9e7236d241ae0d7c5c7b80","last_reissued_at":"2026-07-05T08:36:22.902045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:22.902045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Computational-Statistical Gaps for Improper Learning in Sparse Linear Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Jingqiu Ding, Rares-Darius Buhai, Stefan Tiegel","submitted_at":"2024-02-21T19:55:01Z","abstract_excerpt":"We study computational-statistical gaps for improper learning in sparse linear regression. More specifically, given $n$ samples from a $k$-sparse linear model in dimension $d$, we ask what is the minimum sample complexity to efficiently (in time polynomial in $d$, $k$, and $n$) find a potentially dense estimate for the regression vector that achieves non-trivial prediction error on the $n$ samples. Information-theoretically this can be achieved using $\\Theta(k \\log (d/k))$ samples. Yet, despite its prominence in the literature, there is no polynomial-time algorithm known to achieve the same gu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14103","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/2402.14103/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":"2402.14103","created_at":"2026-07-05T08:36:22.902144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14103v2","created_at":"2026-07-05T08:36:22.902144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14103","created_at":"2026-07-05T08:36:22.902144+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4JNB3I4H773","created_at":"2026-07-05T08:36:22.902144+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4JNB3I4H773OCOR","created_at":"2026-07-05T08:36:22.902144+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4JNB3I4","created_at":"2026-07-05T08:36:22.902144+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17360","citing_title":"The Quasi-Polynomial Low-Degree Conjecture is False","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A4JNB3I4H773OCORTGXDJEGPQX","json":"https://pith.science/pith/A4JNB3I4H773OCORTGXDJEGPQX.json","graph_json":"https://pith.science/api/pith-number/A4JNB3I4H773OCORTGXDJEGPQX/graph.json","events_json":"https://pith.science/api/pith-number/A4JNB3I4H773OCORTGXDJEGPQX/events.json","paper":"https://pith.science/paper/A4JNB3I4"},"agent_actions":{"view_html":"https://pith.science/pith/A4JNB3I4H773OCORTGXDJEGPQX","download_json":"https://pith.science/pith/A4JNB3I4H773OCORTGXDJEGPQX.json","view_paper":"https://pith.science/paper/A4JNB3I4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14103&json=true","fetch_graph":"https://pith.science/api/pith-number/A4JNB3I4H773OCORTGXDJEGPQX/graph.json","fetch_events":"https://pith.science/api/pith-number/A4JNB3I4H773OCORTGXDJEGPQX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4JNB3I4H773OCORTGXDJEGPQX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4JNB3I4H773OCORTGXDJEGPQX/action/storage_attestation","attest_author":"https://pith.science/pith/A4JNB3I4H773OCORTGXDJEGPQX/action/author_attestation","sign_citation":"https://pith.science/pith/A4JNB3I4H773OCORTGXDJEGPQX/action/citation_signature","submit_replication":"https://pith.science/pith/A4JNB3I4H773OCORTGXDJEGPQX/action/replication_record"}},"created_at":"2026-07-05T08:36:22.902144+00:00","updated_at":"2026-07-05T08:36:22.902144+00:00"}