{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BNL4NNOLIPDFTNYKRYK7JPUDF4","short_pith_number":"pith:BNL4NNOL","schema_version":"1.0","canonical_sha256":"0b57c6b5cb43c659b70a8e15f4be832f2b7ef44958d6509d9c4806591324f4b4","source":{"kind":"arxiv","id":"2412.09556","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Convergence of Decentralized Gradient Tracking under the KL Property","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY","stat.ML"],"primary_cat":"math.OC","authors_text":"Gesualdo Scutari, Tianyu Cao, Xiaokai Chen","submitted_at":"2024-12-12T18:44:36Z","abstract_excerpt":"We study decentralized multiagent optimization over networks, modeled as undirected graphs. The optimization problem consists of minimizing a nonconvex smooth function plus a convex extended-value function, which enforces constraints or extra structure on the solution (e.g., sparsity, low-rank). We further assume that the objective function satisfies the Kurdyka-{\\L}ojasiewicz (KL) property, with given exponent $\\theta\\in [0,1)$. The KL property is satisfied by several (nonconvex) functions of practical interest, e.g., arising from machine learning applications; in the centralized setting, it "},"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":"2412.09556","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-12-12T18:44:36Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"29c132f020dea7fadf6243a1175793698723e9e4e6f6bbc711b7f071382d476c","abstract_canon_sha256":"86e5b145e78c0f5fc341768517caaa921c3553cbe0de8661517e8f43d113c9fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:26.306406Z","signature_b64":"98KZMkjA7USoPGQ6jcO+9PYtD7Vk3Dh7HnBz+IdIs3qjwkzpb4ckmupITuBhNyVb2O0akV685hS/9idOr2tPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b57c6b5cb43c659b70a8e15f4be832f2b7ef44958d6509d9c4806591324f4b4","last_reissued_at":"2026-07-05T09:48:26.305909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:26.305909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Convergence of Decentralized Gradient Tracking under the KL Property","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY","stat.ML"],"primary_cat":"math.OC","authors_text":"Gesualdo Scutari, Tianyu Cao, Xiaokai Chen","submitted_at":"2024-12-12T18:44:36Z","abstract_excerpt":"We study decentralized multiagent optimization over networks, modeled as undirected graphs. The optimization problem consists of minimizing a nonconvex smooth function plus a convex extended-value function, which enforces constraints or extra structure on the solution (e.g., sparsity, low-rank). We further assume that the objective function satisfies the Kurdyka-{\\L}ojasiewicz (KL) property, with given exponent $\\theta\\in [0,1)$. The KL property is satisfied by several (nonconvex) functions of practical interest, e.g., arising from machine learning applications; in the centralized setting, it "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09556","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.09556/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":"2412.09556","created_at":"2026-07-05T09:48:26.305973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09556v1","created_at":"2026-07-05T09:48:26.305973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09556","created_at":"2026-07-05T09:48:26.305973+00:00"},{"alias_kind":"pith_short_12","alias_value":"BNL4NNOLIPDF","created_at":"2026-07-05T09:48:26.305973+00:00"},{"alias_kind":"pith_short_16","alias_value":"BNL4NNOLIPDFTNYK","created_at":"2026-07-05T09:48:26.305973+00:00"},{"alias_kind":"pith_short_8","alias_value":"BNL4NNOL","created_at":"2026-07-05T09:48:26.305973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.19182","citing_title":"A Unified Algorithm for Nonconvex Decentralized Nonlinear Optimization","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23184","citing_title":"A Unified Fractional Regularization Framework for Sparse Recovery","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BNL4NNOLIPDFTNYKRYK7JPUDF4","json":"https://pith.science/pith/BNL4NNOLIPDFTNYKRYK7JPUDF4.json","graph_json":"https://pith.science/api/pith-number/BNL4NNOLIPDFTNYKRYK7JPUDF4/graph.json","events_json":"https://pith.science/api/pith-number/BNL4NNOLIPDFTNYKRYK7JPUDF4/events.json","paper":"https://pith.science/paper/BNL4NNOL"},"agent_actions":{"view_html":"https://pith.science/pith/BNL4NNOLIPDFTNYKRYK7JPUDF4","download_json":"https://pith.science/pith/BNL4NNOLIPDFTNYKRYK7JPUDF4.json","view_paper":"https://pith.science/paper/BNL4NNOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09556&json=true","fetch_graph":"https://pith.science/api/pith-number/BNL4NNOLIPDFTNYKRYK7JPUDF4/graph.json","fetch_events":"https://pith.science/api/pith-number/BNL4NNOLIPDFTNYKRYK7JPUDF4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BNL4NNOLIPDFTNYKRYK7JPUDF4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BNL4NNOLIPDFTNYKRYK7JPUDF4/action/storage_attestation","attest_author":"https://pith.science/pith/BNL4NNOLIPDFTNYKRYK7JPUDF4/action/author_attestation","sign_citation":"https://pith.science/pith/BNL4NNOLIPDFTNYKRYK7JPUDF4/action/citation_signature","submit_replication":"https://pith.science/pith/BNL4NNOLIPDFTNYKRYK7JPUDF4/action/replication_record"}},"created_at":"2026-07-05T09:48:26.305973+00:00","updated_at":"2026-07-05T09:48:26.305973+00:00"}