{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5TEY45IEGFW4B6TUB3DGSYLTV5","short_pith_number":"pith:5TEY45IE","schema_version":"1.0","canonical_sha256":"ecc98e7504316dc0fa740ec6696173af5b7a885deeef4cc23b9ba743fd249c53","source":{"kind":"arxiv","id":"2002.09268","version":4},"attestation_state":"computed","paper":{"title":"New Bounds For Distributed Mean Estimation and Variance Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dan Alistarh, Niusha Moshrefi, Peter Davies, Saleh Ashkboos, Vijaykrishna Gurunathan","submitted_at":"2020-02-21T13:27:13Z","abstract_excerpt":"We consider the problem of distributed mean estimation (DME), in which $n$ machines are each given a local $d$-dimensional vector $x_v \\in \\mathbb{R}^d$, and must cooperate to estimate the mean of their inputs $\\mu = \\frac 1n\\sum_{v = 1}^n x_v$, while minimizing total communication cost.\n  DME is a fundamental construct in distributed machine learning, and there has been considerable work on variants of this problem, especially in the context of distributed variance reduction for stochastic gradients in parallel SGD. Previous work typically assumes an upper bound on the norm of the input vecto"},"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":"2002.09268","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-21T13:27:13Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"61c2a2aa530dab82cb33192fca5b3df5c50fc15e08c0b96d3388fc15706bb37e","abstract_canon_sha256":"8e62dcc40e2a834983779a8509b86e6e935e6d0f315f62e0c75ceb185a1da98c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:53.144131Z","signature_b64":"DmKtsiXwtdiObP5yPRmfzOgilAyxh9e+JpxwbSiIJXzXTSCrZi4x0wZz5Vkzj3F6hiJbtWanQxpLEN/wfiRxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecc98e7504316dc0fa740ec6696173af5b7a885deeef4cc23b9ba743fd249c53","last_reissued_at":"2026-07-05T02:29:53.143630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:53.143630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"New Bounds For Distributed Mean Estimation and Variance Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dan Alistarh, Niusha Moshrefi, Peter Davies, Saleh Ashkboos, Vijaykrishna Gurunathan","submitted_at":"2020-02-21T13:27:13Z","abstract_excerpt":"We consider the problem of distributed mean estimation (DME), in which $n$ machines are each given a local $d$-dimensional vector $x_v \\in \\mathbb{R}^d$, and must cooperate to estimate the mean of their inputs $\\mu = \\frac 1n\\sum_{v = 1}^n x_v$, while minimizing total communication cost.\n  DME is a fundamental construct in distributed machine learning, and there has been considerable work on variants of this problem, especially in the context of distributed variance reduction for stochastic gradients in parallel SGD. Previous work typically assumes an upper bound on the norm of the input vecto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09268","kind":"arxiv","version":4},"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/2002.09268/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":"2002.09268","created_at":"2026-07-05T02:29:53.143687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.09268v4","created_at":"2026-07-05T02:29:53.143687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09268","created_at":"2026-07-05T02:29:53.143687+00:00"},{"alias_kind":"pith_short_12","alias_value":"5TEY45IEGFW4","created_at":"2026-07-05T02:29:53.143687+00:00"},{"alias_kind":"pith_short_16","alias_value":"5TEY45IEGFW4B6TU","created_at":"2026-07-05T02:29:53.143687+00:00"},{"alias_kind":"pith_short_8","alias_value":"5TEY45IE","created_at":"2026-07-05T02:29:53.143687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.17525","citing_title":"Pushing the Limits of Large Language Model Quantization via the Linearity Theorem","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5TEY45IEGFW4B6TUB3DGSYLTV5","json":"https://pith.science/pith/5TEY45IEGFW4B6TUB3DGSYLTV5.json","graph_json":"https://pith.science/api/pith-number/5TEY45IEGFW4B6TUB3DGSYLTV5/graph.json","events_json":"https://pith.science/api/pith-number/5TEY45IEGFW4B6TUB3DGSYLTV5/events.json","paper":"https://pith.science/paper/5TEY45IE"},"agent_actions":{"view_html":"https://pith.science/pith/5TEY45IEGFW4B6TUB3DGSYLTV5","download_json":"https://pith.science/pith/5TEY45IEGFW4B6TUB3DGSYLTV5.json","view_paper":"https://pith.science/paper/5TEY45IE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.09268&json=true","fetch_graph":"https://pith.science/api/pith-number/5TEY45IEGFW4B6TUB3DGSYLTV5/graph.json","fetch_events":"https://pith.science/api/pith-number/5TEY45IEGFW4B6TUB3DGSYLTV5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5TEY45IEGFW4B6TUB3DGSYLTV5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5TEY45IEGFW4B6TUB3DGSYLTV5/action/storage_attestation","attest_author":"https://pith.science/pith/5TEY45IEGFW4B6TUB3DGSYLTV5/action/author_attestation","sign_citation":"https://pith.science/pith/5TEY45IEGFW4B6TUB3DGSYLTV5/action/citation_signature","submit_replication":"https://pith.science/pith/5TEY45IEGFW4B6TUB3DGSYLTV5/action/replication_record"}},"created_at":"2026-07-05T02:29:53.143687+00:00","updated_at":"2026-07-05T02:29:53.143687+00:00"}