{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5IC55AUOQFLKKLS6S2GA7H7PSF","short_pith_number":"pith:5IC55AUO","schema_version":"1.0","canonical_sha256":"ea05de828e8156a52e5e968c0f9fef9162709dc773e42180126c620099f423c6","source":{"kind":"arxiv","id":"2402.00377","version":2},"attestation_state":"computed","paper":{"title":"Kurdyka-{\\L}ojasiewicz exponent via Hadamard parametrization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hao Wang, Ting Kei Pong, Wenqing Ouyang, Yuncheng Liu","submitted_at":"2024-02-01T06:52:33Z","abstract_excerpt":"We consider a class of $\\ell_1$-regularized optimization problems and the associated smooth \"over-parameterized\" optimization problems built upon the Hadamard parametrization, or equivalently, the Hadamard difference parametrization (HDP). We characterize the set of second-order stationary points of the HDP-based model and show that they correspond to some stationary points of the corresponding $\\ell_1$-regularized model. More importantly, we show that the Kurdyka-Lojasiewicz (KL) exponent of the HDP-based model at a second-order stationary point can be inferred from that of the corresponding "},"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":"2402.00377","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-02-01T06:52:33Z","cross_cats_sorted":[],"title_canon_sha256":"7ccbfa56d527eef9869e6ea6dcd58e53b9fc4da653110732da3902c6d5620ce8","abstract_canon_sha256":"0fa766e5577fbe0b5e329eb783f8304008b2eb95d28bfc6fca7b2848ec4e6d95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:35.607649Z","signature_b64":"Y6JFSXKHdNT5neNqfJFJopSZvdkWdcd/HYeY9EoZ+oIffrG6I42+wwAUOpizNLzS7fMsEAXZRtFlX7J2aToyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea05de828e8156a52e5e968c0f9fef9162709dc773e42180126c620099f423c6","last_reissued_at":"2026-07-05T08:32:35.607060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:35.607060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kurdyka-{\\L}ojasiewicz exponent via Hadamard parametrization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hao Wang, Ting Kei Pong, Wenqing Ouyang, Yuncheng Liu","submitted_at":"2024-02-01T06:52:33Z","abstract_excerpt":"We consider a class of $\\ell_1$-regularized optimization problems and the associated smooth \"over-parameterized\" optimization problems built upon the Hadamard parametrization, or equivalently, the Hadamard difference parametrization (HDP). We characterize the set of second-order stationary points of the HDP-based model and show that they correspond to some stationary points of the corresponding $\\ell_1$-regularized model. More importantly, we show that the Kurdyka-Lojasiewicz (KL) exponent of the HDP-based model at a second-order stationary point can be inferred from that of the corresponding "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00377","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/2402.00377/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":"2402.00377","created_at":"2026-07-05T08:32:35.607138+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.00377v2","created_at":"2026-07-05T08:32:35.607138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00377","created_at":"2026-07-05T08:32:35.607138+00:00"},{"alias_kind":"pith_short_12","alias_value":"5IC55AUOQFLK","created_at":"2026-07-05T08:32:35.607138+00:00"},{"alias_kind":"pith_short_16","alias_value":"5IC55AUOQFLKKLS6","created_at":"2026-07-05T08:32:35.607138+00:00"},{"alias_kind":"pith_short_8","alias_value":"5IC55AUO","created_at":"2026-07-05T08:32:35.607138+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2307.03571","citing_title":"Smoothing the Edges: Smooth Optimization for Sparse Regularization using Hadamard Overparametrization","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5IC55AUOQFLKKLS6S2GA7H7PSF","json":"https://pith.science/pith/5IC55AUOQFLKKLS6S2GA7H7PSF.json","graph_json":"https://pith.science/api/pith-number/5IC55AUOQFLKKLS6S2GA7H7PSF/graph.json","events_json":"https://pith.science/api/pith-number/5IC55AUOQFLKKLS6S2GA7H7PSF/events.json","paper":"https://pith.science/paper/5IC55AUO"},"agent_actions":{"view_html":"https://pith.science/pith/5IC55AUOQFLKKLS6S2GA7H7PSF","download_json":"https://pith.science/pith/5IC55AUOQFLKKLS6S2GA7H7PSF.json","view_paper":"https://pith.science/paper/5IC55AUO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.00377&json=true","fetch_graph":"https://pith.science/api/pith-number/5IC55AUOQFLKKLS6S2GA7H7PSF/graph.json","fetch_events":"https://pith.science/api/pith-number/5IC55AUOQFLKKLS6S2GA7H7PSF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5IC55AUOQFLKKLS6S2GA7H7PSF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5IC55AUOQFLKKLS6S2GA7H7PSF/action/storage_attestation","attest_author":"https://pith.science/pith/5IC55AUOQFLKKLS6S2GA7H7PSF/action/author_attestation","sign_citation":"https://pith.science/pith/5IC55AUOQFLKKLS6S2GA7H7PSF/action/citation_signature","submit_replication":"https://pith.science/pith/5IC55AUOQFLKKLS6S2GA7H7PSF/action/replication_record"}},"created_at":"2026-07-05T08:32:35.607138+00:00","updated_at":"2026-07-05T08:32:35.607138+00:00"}