{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VTPKUNURIPLLNJIUCK2X5UDLYY","short_pith_number":"pith:VTPKUNUR","schema_version":"1.0","canonical_sha256":"acdeaa369143d6b6a51412b57ed06bc63713fa26bdfb91ab1612cbabd694c5be","source":{"kind":"arxiv","id":"1911.07971","version":4},"attestation_state":"computed","paper":{"title":"vqSGD: Vector Quantized Stochastic Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arya Mazumdar, Daniel Kane, Raj Kumar Maity, Venkata Gandikota","submitted_at":"2019-11-18T21:48:01Z","abstract_excerpt":"In this work, we present a family of vector quantization schemes \\emph{vqSGD} (Vector-Quantized Stochastic Gradient Descent) that provide an asymptotic reduction in the communication cost with convergence guarantees in first-order distributed optimization. In the process we derive the following fundamental information theoretic fact: $\\Theta(\\frac{d}{R^2})$ bits are necessary and sufficient to describe an unbiased estimator ${\\hat{g}}({g})$ for any ${g}$ in the $d$-dimensional unit sphere, under the constraint that $\\|{\\hat{g}}({g})\\|_2\\le R$ almost surely. In particular, we consider a randomi"},"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":"1911.07971","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-18T21:48:01Z","cross_cats_sorted":["cs.DC","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"bdc78650cda94fcf1f2ff621bced78d1b3b9091c0ccd9927f0238eac3ab0ea7d","abstract_canon_sha256":"d455f5d431ffb76868b8c198b2fe9195a5d28057d4028da23d50162fd128dd33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:02:01.518293Z","signature_b64":"tVTR6lAhwSEofRLXAHatZvPyAeREYb7/DnyHiVzHFqfpPkNfu+A5GQxeRGaT56xI6iy/RP0kzhmko9SrYbupDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acdeaa369143d6b6a51412b57ed06bc63713fa26bdfb91ab1612cbabd694c5be","last_reissued_at":"2026-07-05T02:02:01.517945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:02:01.517945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"vqSGD: Vector Quantized Stochastic Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arya Mazumdar, Daniel Kane, Raj Kumar Maity, Venkata Gandikota","submitted_at":"2019-11-18T21:48:01Z","abstract_excerpt":"In this work, we present a family of vector quantization schemes \\emph{vqSGD} (Vector-Quantized Stochastic Gradient Descent) that provide an asymptotic reduction in the communication cost with convergence guarantees in first-order distributed optimization. In the process we derive the following fundamental information theoretic fact: $\\Theta(\\frac{d}{R^2})$ bits are necessary and sufficient to describe an unbiased estimator ${\\hat{g}}({g})$ for any ${g}$ in the $d$-dimensional unit sphere, under the constraint that $\\|{\\hat{g}}({g})\\|_2\\le R$ almost surely. In particular, we consider a randomi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.07971","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/1911.07971/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":"1911.07971","created_at":"2026-07-05T02:02:01.518002+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.07971v4","created_at":"2026-07-05T02:02:01.518002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.07971","created_at":"2026-07-05T02:02:01.518002+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTPKUNURIPLL","created_at":"2026-07-05T02:02:01.518002+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTPKUNURIPLLNJIU","created_at":"2026-07-05T02:02:01.518002+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTPKUNUR","created_at":"2026-07-05T02:02:01.518002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08233","citing_title":"Strategies for Improving Communication Efficiency in Distributed and Federated Learning: Compression, Local Training, and Personalization","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VTPKUNURIPLLNJIUCK2X5UDLYY","json":"https://pith.science/pith/VTPKUNURIPLLNJIUCK2X5UDLYY.json","graph_json":"https://pith.science/api/pith-number/VTPKUNURIPLLNJIUCK2X5UDLYY/graph.json","events_json":"https://pith.science/api/pith-number/VTPKUNURIPLLNJIUCK2X5UDLYY/events.json","paper":"https://pith.science/paper/VTPKUNUR"},"agent_actions":{"view_html":"https://pith.science/pith/VTPKUNURIPLLNJIUCK2X5UDLYY","download_json":"https://pith.science/pith/VTPKUNURIPLLNJIUCK2X5UDLYY.json","view_paper":"https://pith.science/paper/VTPKUNUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.07971&json=true","fetch_graph":"https://pith.science/api/pith-number/VTPKUNURIPLLNJIUCK2X5UDLYY/graph.json","fetch_events":"https://pith.science/api/pith-number/VTPKUNURIPLLNJIUCK2X5UDLYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTPKUNURIPLLNJIUCK2X5UDLYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTPKUNURIPLLNJIUCK2X5UDLYY/action/storage_attestation","attest_author":"https://pith.science/pith/VTPKUNURIPLLNJIUCK2X5UDLYY/action/author_attestation","sign_citation":"https://pith.science/pith/VTPKUNURIPLLNJIUCK2X5UDLYY/action/citation_signature","submit_replication":"https://pith.science/pith/VTPKUNURIPLLNJIUCK2X5UDLYY/action/replication_record"}},"created_at":"2026-07-05T02:02:01.518002+00:00","updated_at":"2026-07-05T02:02:01.518002+00:00"}