{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YTZYDLGDKSIHO4CSKTGWXIRSQR","short_pith_number":"pith:YTZYDLGD","schema_version":"1.0","canonical_sha256":"c4f381acc3549077705254cd6ba2328448632108898a53cf04bd1a2ef870e552","source":{"kind":"arxiv","id":"1902.11259","version":2},"attestation_state":"computed","paper":{"title":"Distributed Learning with Sublinear Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher De Sa, Dylan J. Foster, Jayadev Acharya, Karthik Sridharan","submitted_at":"2019-02-28T18:05:12Z","abstract_excerpt":"In distributed statistical learning, $N$ samples are split across $m$ machines and a learner wishes to use minimal communication to learn as well as if the examples were on a single machine. This model has received substantial interest in machine learning due to its scalability and potential for parallel speedup. However, in high-dimensional settings, where the number examples is smaller than the number of features (\"dimension\"), the speedup afforded by distributed learning may be overshadowed by the cost of communicating a single example. This paper investigates the following question: When i"},"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":"1902.11259","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-28T18:05:12Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"604c30e0e4d5a2f26fafa13073df395e06892fa3695f5a253007767a38b1999c","abstract_canon_sha256":"337e77ba5c1e6ad12d6c028e26713a634c8e636b85803f7ab66e33a29e3b56d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:04.899746Z","signature_b64":"LMiCk9DUHpIOTMqCSjNQcbAj7bkBUN6tZBY78Ya4S+XKmqu7/IsShQYkp4sRkaLDqgQ8DoBodTEtF4Z4ElN/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4f381acc3549077705254cd6ba2328448632108898a53cf04bd1a2ef870e552","last_reissued_at":"2026-05-17T23:51:04.899149Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:04.899149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed Learning with Sublinear Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher De Sa, Dylan J. Foster, Jayadev Acharya, Karthik Sridharan","submitted_at":"2019-02-28T18:05:12Z","abstract_excerpt":"In distributed statistical learning, $N$ samples are split across $m$ machines and a learner wishes to use minimal communication to learn as well as if the examples were on a single machine. This model has received substantial interest in machine learning due to its scalability and potential for parallel speedup. However, in high-dimensional settings, where the number examples is smaller than the number of features (\"dimension\"), the speedup afforded by distributed learning may be overshadowed by the cost of communicating a single example. This paper investigates the following question: When i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.11259","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":""},"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":"1902.11259","created_at":"2026-05-17T23:51:04.899258+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.11259v2","created_at":"2026-05-17T23:51:04.899258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.11259","created_at":"2026-05-17T23:51:04.899258+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTZYDLGDKSIH","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTZYDLGDKSIHO4CS","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTZYDLGD","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.08200","citing_title":"RATQ: A Universal Fixed-Length Quantizer for Stochastic Optimization","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YTZYDLGDKSIHO4CSKTGWXIRSQR","json":"https://pith.science/pith/YTZYDLGDKSIHO4CSKTGWXIRSQR.json","graph_json":"https://pith.science/api/pith-number/YTZYDLGDKSIHO4CSKTGWXIRSQR/graph.json","events_json":"https://pith.science/api/pith-number/YTZYDLGDKSIHO4CSKTGWXIRSQR/events.json","paper":"https://pith.science/paper/YTZYDLGD"},"agent_actions":{"view_html":"https://pith.science/pith/YTZYDLGDKSIHO4CSKTGWXIRSQR","download_json":"https://pith.science/pith/YTZYDLGDKSIHO4CSKTGWXIRSQR.json","view_paper":"https://pith.science/paper/YTZYDLGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.11259&json=true","fetch_graph":"https://pith.science/api/pith-number/YTZYDLGDKSIHO4CSKTGWXIRSQR/graph.json","fetch_events":"https://pith.science/api/pith-number/YTZYDLGDKSIHO4CSKTGWXIRSQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTZYDLGDKSIHO4CSKTGWXIRSQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTZYDLGDKSIHO4CSKTGWXIRSQR/action/storage_attestation","attest_author":"https://pith.science/pith/YTZYDLGDKSIHO4CSKTGWXIRSQR/action/author_attestation","sign_citation":"https://pith.science/pith/YTZYDLGDKSIHO4CSKTGWXIRSQR/action/citation_signature","submit_replication":"https://pith.science/pith/YTZYDLGDKSIHO4CSKTGWXIRSQR/action/replication_record"}},"created_at":"2026-05-17T23:51:04.899258+00:00","updated_at":"2026-05-17T23:51:04.899258+00:00"}