{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UXMQUYH4JTXA6UAYOB7JV3KJYL","short_pith_number":"pith:UXMQUYH4","schema_version":"1.0","canonical_sha256":"a5d90a60fc4cee0f5018707e9aed49c2c659ca28608d3eac71e19e362ba0d817","source":{"kind":"arxiv","id":"2006.01065","version":2},"attestation_state":"computed","paper":{"title":"Hadamard Wirtinger Flow for Sparse Phase Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.SP"],"primary_cat":"stat.ML","authors_text":"Fan Wu, Patrick Rebeschini","submitted_at":"2020-06-01T16:41:27Z","abstract_excerpt":"We consider the problem of reconstructing an $n$-dimensional $k$-sparse signal from a set of noiseless magnitude-only measurements. Formulating the problem as an unregularized empirical risk minimization task, we study the sample complexity performance of gradient descent with Hadamard parametrization, which we call Hadamard Wirtinger flow (HWF). Provided knowledge of the signal sparsity $k$, we prove that a single step of HWF is able to recover the support from $k(x^*_{max})^{-2}$ (modulo logarithmic term) samples, where $x^*_{max}$ is the largest component of the signal in magnitude. This su"},"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":"2006.01065","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-01T16:41:27Z","cross_cats_sorted":["cs.LG","eess.SP"],"title_canon_sha256":"cfff6b67d6f151f6bd92ccde3520145ed409022259ee22c099589cf2f02aa235","abstract_canon_sha256":"ed3d370674593440eb128e0e55f01f34ccd2d396f762e2574fa4702b9eeefb9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:18:04.994152Z","signature_b64":"FXDbE+gZIEJYzWEaGKFZDXeMwztQAY3E62YRzvZbvKj5A/0dT+tvezHzQhdbRq6KDhJteHfvoBXQskzjkIDFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5d90a60fc4cee0f5018707e9aed49c2c659ca28608d3eac71e19e362ba0d817","last_reissued_at":"2026-07-05T02:18:04.993779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:18:04.993779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hadamard Wirtinger Flow for Sparse Phase Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.SP"],"primary_cat":"stat.ML","authors_text":"Fan Wu, Patrick Rebeschini","submitted_at":"2020-06-01T16:41:27Z","abstract_excerpt":"We consider the problem of reconstructing an $n$-dimensional $k$-sparse signal from a set of noiseless magnitude-only measurements. Formulating the problem as an unregularized empirical risk minimization task, we study the sample complexity performance of gradient descent with Hadamard parametrization, which we call Hadamard Wirtinger flow (HWF). Provided knowledge of the signal sparsity $k$, we prove that a single step of HWF is able to recover the support from $k(x^*_{max})^{-2}$ (modulo logarithmic term) samples, where $x^*_{max}$ is the largest component of the signal in magnitude. This su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.01065","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/2006.01065/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":"2006.01065","created_at":"2026-07-05T02:18:04.993835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.01065v2","created_at":"2026-07-05T02:18:04.993835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.01065","created_at":"2026-07-05T02:18:04.993835+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXMQUYH4JTXA","created_at":"2026-07-05T02:18:04.993835+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXMQUYH4JTXA6UAY","created_at":"2026-07-05T02:18:04.993835+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXMQUYH4","created_at":"2026-07-05T02:18:04.993835+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/UXMQUYH4JTXA6UAYOB7JV3KJYL","json":"https://pith.science/pith/UXMQUYH4JTXA6UAYOB7JV3KJYL.json","graph_json":"https://pith.science/api/pith-number/UXMQUYH4JTXA6UAYOB7JV3KJYL/graph.json","events_json":"https://pith.science/api/pith-number/UXMQUYH4JTXA6UAYOB7JV3KJYL/events.json","paper":"https://pith.science/paper/UXMQUYH4"},"agent_actions":{"view_html":"https://pith.science/pith/UXMQUYH4JTXA6UAYOB7JV3KJYL","download_json":"https://pith.science/pith/UXMQUYH4JTXA6UAYOB7JV3KJYL.json","view_paper":"https://pith.science/paper/UXMQUYH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.01065&json=true","fetch_graph":"https://pith.science/api/pith-number/UXMQUYH4JTXA6UAYOB7JV3KJYL/graph.json","fetch_events":"https://pith.science/api/pith-number/UXMQUYH4JTXA6UAYOB7JV3KJYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXMQUYH4JTXA6UAYOB7JV3KJYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXMQUYH4JTXA6UAYOB7JV3KJYL/action/storage_attestation","attest_author":"https://pith.science/pith/UXMQUYH4JTXA6UAYOB7JV3KJYL/action/author_attestation","sign_citation":"https://pith.science/pith/UXMQUYH4JTXA6UAYOB7JV3KJYL/action/citation_signature","submit_replication":"https://pith.science/pith/UXMQUYH4JTXA6UAYOB7JV3KJYL/action/replication_record"}},"created_at":"2026-07-05T02:18:04.993835+00:00","updated_at":"2026-07-05T02:18:04.993835+00:00"}