{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZJXW5TUFD5DV3KLHEB3KAA5IQ6","short_pith_number":"pith:ZJXW5TUF","schema_version":"1.0","canonical_sha256":"ca6f6ece851f475da9672076a003a88796f1f04a19fb4c6c925200ff783f2d8a","source":{"kind":"arxiv","id":"2412.17054","version":1},"attestation_state":"computed","paper":{"title":"Differentially Private Random Block Coordinate Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Abdurakhmon Sadiev, Artavazd Maranjyan, Peter Richt\\'arik","submitted_at":"2024-12-22T15:06:56Z","abstract_excerpt":"Coordinate Descent (CD) methods have gained significant attention in machine learning due to their effectiveness in solving high-dimensional problems and their ability to decompose complex optimization tasks. However, classical CD methods were neither designed nor analyzed with data privacy in mind, a critical concern when handling sensitive information. This has led to the development of differentially private CD methods, such as DP-CD (Differentially Private Coordinate Descent) proposed by Mangold et al. (ICML 2022), yet a disparity remains between non-private CD and DP-CD methods. In our wo"},"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":"2412.17054","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-12-22T15:06:56Z","cross_cats_sorted":["cs.CR","cs.LG","stat.ML"],"title_canon_sha256":"a7e49afb4021a93631c2fc779c8dfef897233978adb9483ac6fcd29948ee4d41","abstract_canon_sha256":"5e5074f19b9fa8f8af5e304feb1875f6c936243b900d5f9bf622beeea1578bac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:16.982468Z","signature_b64":"KlGHdG2gUtwALyiuPdLJ4nq3Wa2oPWtPjzbNfRPVlHOp4MBU35WKnHvdmZwlVbUSLgc+6Me6JMeAu8PrEu+EAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca6f6ece851f475da9672076a003a88796f1f04a19fb4c6c925200ff783f2d8a","last_reissued_at":"2026-07-05T09:53:16.982075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:16.982075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentially Private Random Block Coordinate Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Abdurakhmon Sadiev, Artavazd Maranjyan, Peter Richt\\'arik","submitted_at":"2024-12-22T15:06:56Z","abstract_excerpt":"Coordinate Descent (CD) methods have gained significant attention in machine learning due to their effectiveness in solving high-dimensional problems and their ability to decompose complex optimization tasks. However, classical CD methods were neither designed nor analyzed with data privacy in mind, a critical concern when handling sensitive information. This has led to the development of differentially private CD methods, such as DP-CD (Differentially Private Coordinate Descent) proposed by Mangold et al. (ICML 2022), yet a disparity remains between non-private CD and DP-CD methods. In our wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17054","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/2412.17054/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":"2412.17054","created_at":"2026-07-05T09:53:16.982129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17054v1","created_at":"2026-07-05T09:53:16.982129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17054","created_at":"2026-07-05T09:53:16.982129+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJXW5TUFD5DV","created_at":"2026-07-05T09:53:16.982129+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJXW5TUFD5DV3KLH","created_at":"2026-07-05T09:53:16.982129+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJXW5TUF","created_at":"2026-07-05T09:53:16.982129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20866","citing_title":"LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18174","citing_title":"Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13434","citing_title":"Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08871","citing_title":"Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJXW5TUFD5DV3KLHEB3KAA5IQ6","json":"https://pith.science/pith/ZJXW5TUFD5DV3KLHEB3KAA5IQ6.json","graph_json":"https://pith.science/api/pith-number/ZJXW5TUFD5DV3KLHEB3KAA5IQ6/graph.json","events_json":"https://pith.science/api/pith-number/ZJXW5TUFD5DV3KLHEB3KAA5IQ6/events.json","paper":"https://pith.science/paper/ZJXW5TUF"},"agent_actions":{"view_html":"https://pith.science/pith/ZJXW5TUFD5DV3KLHEB3KAA5IQ6","download_json":"https://pith.science/pith/ZJXW5TUFD5DV3KLHEB3KAA5IQ6.json","view_paper":"https://pith.science/paper/ZJXW5TUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17054&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJXW5TUFD5DV3KLHEB3KAA5IQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJXW5TUFD5DV3KLHEB3KAA5IQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJXW5TUFD5DV3KLHEB3KAA5IQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJXW5TUFD5DV3KLHEB3KAA5IQ6/action/storage_attestation","attest_author":"https://pith.science/pith/ZJXW5TUFD5DV3KLHEB3KAA5IQ6/action/author_attestation","sign_citation":"https://pith.science/pith/ZJXW5TUFD5DV3KLHEB3KAA5IQ6/action/citation_signature","submit_replication":"https://pith.science/pith/ZJXW5TUFD5DV3KLHEB3KAA5IQ6/action/replication_record"}},"created_at":"2026-07-05T09:53:16.982129+00:00","updated_at":"2026-07-05T09:53:16.982129+00:00"}