{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:WZHQRF5TEXWZKVVFKLDWNDIK4Z","short_pith_number":"pith:WZHQRF5T","schema_version":"1.0","canonical_sha256":"b64f0897b325ed9556a552c7668d0ae65d94f4c61f1ad5cfa5c5bf96a3546f8c","source":{"kind":"arxiv","id":"1611.00429","version":3},"attestation_state":"computed","paper":{"title":"Distributed Mean Estimation with Limited Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ananda Theertha Suresh, Felix X. Yu, H. Brendan McMahan, Sanjiv Kumar","submitted_at":"2016-11-02T00:16:18Z","abstract_excerpt":"Motivated by the need for distributed learning and optimization algorithms with low communication cost, we study communication efficient algorithms for distributed mean estimation. Unlike previous works, we make no probabilistic assumptions on the data. We first show that for $d$ dimensional data with $n$ clients, a naive stochastic binary rounding approach yields a mean squared error (MSE) of $\\Theta(d/n)$ and uses a constant number of bits per dimension per client. We then extend this naive algorithm in two ways: we show that applying a structured random rotation before quantization reduces "},"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":"1611.00429","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-02T00:16:18Z","cross_cats_sorted":[],"title_canon_sha256":"6fe80dffbdf1ba656f9945d01ead5ba287df55ca5f0469cf912e4b6722ccfa68","abstract_canon_sha256":"12bbba583bca6df5a697093a3c80d29d96dc49a8e57b3f3b8b070f9e266ccfab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:31.461529Z","signature_b64":"aDOAwoRSebfwHKcOLwSGQLsEpiQxeH9UKeGbPe+BWRGwt9wGPYCa8/y8Huh3/GBBXX21C1+2DHElbkbm04Z2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b64f0897b325ed9556a552c7668d0ae65d94f4c61f1ad5cfa5c5bf96a3546f8c","last_reissued_at":"2026-05-18T00:34:31.461091Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:31.461091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed Mean Estimation with Limited Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ananda Theertha Suresh, Felix X. Yu, H. Brendan McMahan, Sanjiv Kumar","submitted_at":"2016-11-02T00:16:18Z","abstract_excerpt":"Motivated by the need for distributed learning and optimization algorithms with low communication cost, we study communication efficient algorithms for distributed mean estimation. Unlike previous works, we make no probabilistic assumptions on the data. We first show that for $d$ dimensional data with $n$ clients, a naive stochastic binary rounding approach yields a mean squared error (MSE) of $\\Theta(d/n)$ and uses a constant number of bits per dimension per client. We then extend this naive algorithm in two ways: we show that applying a structured random rotation before quantization reduces "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.00429","kind":"arxiv","version":3},"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":"1611.00429","created_at":"2026-05-18T00:34:31.461160+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.00429v3","created_at":"2026-05-18T00:34:31.461160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.00429","created_at":"2026-05-18T00:34:31.461160+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZHQRF5TEXWZ","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZHQRF5TEXWZKVVF","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZHQRF5T","created_at":"2026-05-18T12:30:51.357362+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/WZHQRF5TEXWZKVVFKLDWNDIK4Z","json":"https://pith.science/pith/WZHQRF5TEXWZKVVFKLDWNDIK4Z.json","graph_json":"https://pith.science/api/pith-number/WZHQRF5TEXWZKVVFKLDWNDIK4Z/graph.json","events_json":"https://pith.science/api/pith-number/WZHQRF5TEXWZKVVFKLDWNDIK4Z/events.json","paper":"https://pith.science/paper/WZHQRF5T"},"agent_actions":{"view_html":"https://pith.science/pith/WZHQRF5TEXWZKVVFKLDWNDIK4Z","download_json":"https://pith.science/pith/WZHQRF5TEXWZKVVFKLDWNDIK4Z.json","view_paper":"https://pith.science/paper/WZHQRF5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.00429&json=true","fetch_graph":"https://pith.science/api/pith-number/WZHQRF5TEXWZKVVFKLDWNDIK4Z/graph.json","fetch_events":"https://pith.science/api/pith-number/WZHQRF5TEXWZKVVFKLDWNDIK4Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZHQRF5TEXWZKVVFKLDWNDIK4Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZHQRF5TEXWZKVVFKLDWNDIK4Z/action/storage_attestation","attest_author":"https://pith.science/pith/WZHQRF5TEXWZKVVFKLDWNDIK4Z/action/author_attestation","sign_citation":"https://pith.science/pith/WZHQRF5TEXWZKVVFKLDWNDIK4Z/action/citation_signature","submit_replication":"https://pith.science/pith/WZHQRF5TEXWZKVVFKLDWNDIK4Z/action/replication_record"}},"created_at":"2026-05-18T00:34:31.461160+00:00","updated_at":"2026-05-18T00:34:31.461160+00:00"}