{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:35MELYIDIJCZ7D4RQIUI2QR5CJ","short_pith_number":"pith:35MELYID","schema_version":"1.0","canonical_sha256":"df5845e10342459f8f9182288d423d1271dda1d6d7aac1b178d5cf541d53394c","source":{"kind":"arxiv","id":"1810.03340","version":1},"attestation_state":"computed","paper":{"title":"Support Localization and the Fisher Metric for off-the-grid Sparse Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT"],"primary_cat":"cs.IT","authors_text":"Clarice Poon, Gabriel Peyr\\'e, Nicolas Keriven","submitted_at":"2018-10-08T09:28:43Z","abstract_excerpt":"Sparse regularization is a central technique for both machine learning (to achieve supervised features selection or unsupervised mixture learning) and imaging sciences (to achieve super-resolution). Existing performance guaranties assume a separation of the spikes based on an ad-hoc (usually Euclidean) minimum distance condition, which ignores the geometry of the problem. In this article, we study the BLASSO (i.e. the off-the-grid version of $\\ell^1$ LASSO regularization) and show that the Fisher-Rao distance is the natural way to ensure and quantify support recovery, since it preserves the in"},"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":"1810.03340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2018-10-08T09:28:43Z","cross_cats_sorted":["math.IT"],"title_canon_sha256":"394218ed1ac89fe191531571d9c062c78ce0370506d9877448eb35eaa048ede6","abstract_canon_sha256":"7c66881476c1a1adc7da5153cc4e175ebecfd9c386c5947f3876691649d984e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:51.618146Z","signature_b64":"avCdu8jcAqDruQENbhQ3uriNBMplfyBp67sSkMkkqzwGfVdRVRHrMCe4AtQCTdFaT1ry6+aVemfqyerSa9rCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df5845e10342459f8f9182288d423d1271dda1d6d7aac1b178d5cf541d53394c","last_reissued_at":"2026-05-18T00:03:51.617344Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:51.617344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Support Localization and the Fisher Metric for off-the-grid Sparse Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT"],"primary_cat":"cs.IT","authors_text":"Clarice Poon, Gabriel Peyr\\'e, Nicolas Keriven","submitted_at":"2018-10-08T09:28:43Z","abstract_excerpt":"Sparse regularization is a central technique for both machine learning (to achieve supervised features selection or unsupervised mixture learning) and imaging sciences (to achieve super-resolution). Existing performance guaranties assume a separation of the spikes based on an ad-hoc (usually Euclidean) minimum distance condition, which ignores the geometry of the problem. In this article, we study the BLASSO (i.e. the off-the-grid version of $\\ell^1$ LASSO regularization) and show that the Fisher-Rao distance is the natural way to ensure and quantify support recovery, since it preserves the in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03340","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":"1810.03340","created_at":"2026-05-18T00:03:51.617486+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.03340v1","created_at":"2026-05-18T00:03:51.617486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03340","created_at":"2026-05-18T00:03:51.617486+00:00"},{"alias_kind":"pith_short_12","alias_value":"35MELYIDIJCZ","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"35MELYIDIJCZ7D4R","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"35MELYID","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09919","citing_title":"On the linear convergence rates of exchange and continuous methods for total variation minimization","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/35MELYIDIJCZ7D4RQIUI2QR5CJ","json":"https://pith.science/pith/35MELYIDIJCZ7D4RQIUI2QR5CJ.json","graph_json":"https://pith.science/api/pith-number/35MELYIDIJCZ7D4RQIUI2QR5CJ/graph.json","events_json":"https://pith.science/api/pith-number/35MELYIDIJCZ7D4RQIUI2QR5CJ/events.json","paper":"https://pith.science/paper/35MELYID"},"agent_actions":{"view_html":"https://pith.science/pith/35MELYIDIJCZ7D4RQIUI2QR5CJ","download_json":"https://pith.science/pith/35MELYIDIJCZ7D4RQIUI2QR5CJ.json","view_paper":"https://pith.science/paper/35MELYID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.03340&json=true","fetch_graph":"https://pith.science/api/pith-number/35MELYIDIJCZ7D4RQIUI2QR5CJ/graph.json","fetch_events":"https://pith.science/api/pith-number/35MELYIDIJCZ7D4RQIUI2QR5CJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35MELYIDIJCZ7D4RQIUI2QR5CJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35MELYIDIJCZ7D4RQIUI2QR5CJ/action/storage_attestation","attest_author":"https://pith.science/pith/35MELYIDIJCZ7D4RQIUI2QR5CJ/action/author_attestation","sign_citation":"https://pith.science/pith/35MELYIDIJCZ7D4RQIUI2QR5CJ/action/citation_signature","submit_replication":"https://pith.science/pith/35MELYIDIJCZ7D4RQIUI2QR5CJ/action/replication_record"}},"created_at":"2026-05-18T00:03:51.617486+00:00","updated_at":"2026-05-18T00:03:51.617486+00:00"}