{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TMMVUHJIKJMZHRW4ELB5RWD3DA","short_pith_number":"pith:TMMVUHJI","schema_version":"1.0","canonical_sha256":"9b195a1d28525993c6dc22c3d8d87b182d592e08e6715c8bf9ac812d3a6152a6","source":{"kind":"arxiv","id":"2004.14180","version":2},"attestation_state":"computed","paper":{"title":"Quantized Adam with Error Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Congliang Chen, Haozhi Huang, Li Shen, Wei Liu","submitted_at":"2020-04-29T13:21:54Z","abstract_excerpt":"In this paper, we present a distributed variant of adaptive stochastic gradient method for training deep neural networks in the parameter-server model. To reduce the communication cost among the workers and server, we incorporate two types of quantization schemes, i.e., gradient quantization and weight quantization, into the proposed distributed Adam. Besides, to reduce the bias introduced by quantization operations, we propose an error-feedback technique to compensate for the quantized gradient. Theoretically, in the stochastic nonconvex setting, we show that the distributed adaptive gradient"},"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":"2004.14180","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-04-29T13:21:54Z","cross_cats_sorted":["cs.DC","math.OC","stat.ML"],"title_canon_sha256":"bb41618ca528264ab06fa7aefffcc32928a05b728d06422ba7789a845eac877a","abstract_canon_sha256":"07d64caf35ba3bfe1f207786cfd9ee3efeb7373d3c2ff85d14731e0e688a1f8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:10.464508Z","signature_b64":"XmXkU+5rMohTVwr6xDz1xuqkUbeDuQC2TPeHpQhqLfvOnS0vBygr15tpGrHsDOixPoZhjTXoRUfuyY40+b8JCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b195a1d28525993c6dc22c3d8d87b182d592e08e6715c8bf9ac812d3a6152a6","last_reissued_at":"2026-07-05T02:49:10.464043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:10.464043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantized Adam with Error Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Congliang Chen, Haozhi Huang, Li Shen, Wei Liu","submitted_at":"2020-04-29T13:21:54Z","abstract_excerpt":"In this paper, we present a distributed variant of adaptive stochastic gradient method for training deep neural networks in the parameter-server model. To reduce the communication cost among the workers and server, we incorporate two types of quantization schemes, i.e., gradient quantization and weight quantization, into the proposed distributed Adam. Besides, to reduce the bias introduced by quantization operations, we propose an error-feedback technique to compensate for the quantized gradient. Theoretically, in the stochastic nonconvex setting, we show that the distributed adaptive gradient"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14180","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.14180/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":"2004.14180","created_at":"2026-07-05T02:49:10.464096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.14180v2","created_at":"2026-07-05T02:49:10.464096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14180","created_at":"2026-07-05T02:49:10.464096+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMMVUHJIKJMZ","created_at":"2026-07-05T02:49:10.464096+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMMVUHJIKJMZHRW4","created_at":"2026-07-05T02:49:10.464096+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMMVUHJI","created_at":"2026-07-05T02:49:10.464096+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04243","citing_title":"Temporal Reasoning Is Not the Bottleneck: A Probabilistic Inconsistency Framework for Neuro-Symbolic QA","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TMMVUHJIKJMZHRW4ELB5RWD3DA","json":"https://pith.science/pith/TMMVUHJIKJMZHRW4ELB5RWD3DA.json","graph_json":"https://pith.science/api/pith-number/TMMVUHJIKJMZHRW4ELB5RWD3DA/graph.json","events_json":"https://pith.science/api/pith-number/TMMVUHJIKJMZHRW4ELB5RWD3DA/events.json","paper":"https://pith.science/paper/TMMVUHJI"},"agent_actions":{"view_html":"https://pith.science/pith/TMMVUHJIKJMZHRW4ELB5RWD3DA","download_json":"https://pith.science/pith/TMMVUHJIKJMZHRW4ELB5RWD3DA.json","view_paper":"https://pith.science/paper/TMMVUHJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.14180&json=true","fetch_graph":"https://pith.science/api/pith-number/TMMVUHJIKJMZHRW4ELB5RWD3DA/graph.json","fetch_events":"https://pith.science/api/pith-number/TMMVUHJIKJMZHRW4ELB5RWD3DA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMMVUHJIKJMZHRW4ELB5RWD3DA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMMVUHJIKJMZHRW4ELB5RWD3DA/action/storage_attestation","attest_author":"https://pith.science/pith/TMMVUHJIKJMZHRW4ELB5RWD3DA/action/author_attestation","sign_citation":"https://pith.science/pith/TMMVUHJIKJMZHRW4ELB5RWD3DA/action/citation_signature","submit_replication":"https://pith.science/pith/TMMVUHJIKJMZHRW4ELB5RWD3DA/action/replication_record"}},"created_at":"2026-07-05T02:49:10.464096+00:00","updated_at":"2026-07-05T02:49:10.464096+00:00"}