{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PJ7CADNDDTVGKADSJWCSTI4GDA","short_pith_number":"pith:PJ7CADND","schema_version":"1.0","canonical_sha256":"7a7e200da31cea6500724d8529a3861809c63f1e1c1c20f0e6edbbd024f403fe","source":{"kind":"arxiv","id":"1803.05880","version":1},"attestation_state":"computed","paper":{"title":"GossipGraD: Scalable Deep Learning using Gossip Communication based Asynchronous Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Abhinav Vishnu, Charles Siegel, Jeff Daily, Thomas Warfel, Vinay Amatya","submitted_at":"2018-03-15T17:32:16Z","abstract_excerpt":"In this paper, we present GossipGraD - a gossip communication protocol based Stochastic Gradient Descent (SGD) algorithm for scaling Deep Learning (DL) algorithms on large-scale systems. The salient features of GossipGraD are: 1) reduction in overall communication complexity from {\\Theta}(log(p)) for p compute nodes in well-studied SGD to O(1), 2) model diffusion such that compute nodes exchange their updates (gradients) indirectly after every log(p) steps, 3) rotation of communication partners for facilitating direct diffusion of gradients, 4) asynchronous distributed shuffle of samples durin"},"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":"1803.05880","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-03-15T17:32:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"823f0e69a560511253d1931791403105687d1d9ff6474ac071e8d5fbef785eb1","abstract_canon_sha256":"0d8d510d8ff2ea6637ee5cd37df8877ebe3a5f2ee528037738fccd28b5c38d34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:54.457041Z","signature_b64":"fmlCW0A+IfvXZMhISRi3Z3VsC4DP55h322+pubXwVDmCbkrd1jKkBhrNJzklDunRzun/kWmvvDg+flz13fPKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a7e200da31cea6500724d8529a3861809c63f1e1c1c20f0e6edbbd024f403fe","last_reissued_at":"2026-05-18T00:20:54.456602Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:54.456602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GossipGraD: Scalable Deep Learning using Gossip Communication based Asynchronous Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Abhinav Vishnu, Charles Siegel, Jeff Daily, Thomas Warfel, Vinay Amatya","submitted_at":"2018-03-15T17:32:16Z","abstract_excerpt":"In this paper, we present GossipGraD - a gossip communication protocol based Stochastic Gradient Descent (SGD) algorithm for scaling Deep Learning (DL) algorithms on large-scale systems. The salient features of GossipGraD are: 1) reduction in overall communication complexity from {\\Theta}(log(p)) for p compute nodes in well-studied SGD to O(1), 2) model diffusion such that compute nodes exchange their updates (gradients) indirectly after every log(p) steps, 3) rotation of communication partners for facilitating direct diffusion of gradients, 4) asynchronous distributed shuffle of samples durin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.05880","kind":"arxiv","version":1},"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":"1803.05880","created_at":"2026-05-18T00:20:54.456668+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.05880v1","created_at":"2026-05-18T00:20:54.456668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.05880","created_at":"2026-05-18T00:20:54.456668+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJ7CADNDDTVG","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJ7CADNDDTVGKADS","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJ7CADND","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16184","citing_title":"Runtime-Orchestrated Second-Order Optimization for Scalable LLM Training","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23980","citing_title":"SUDA-Muon: Structural Design Principles and Boundaries for Fully Decentralized Muon","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJ7CADNDDTVGKADSJWCSTI4GDA","json":"https://pith.science/pith/PJ7CADNDDTVGKADSJWCSTI4GDA.json","graph_json":"https://pith.science/api/pith-number/PJ7CADNDDTVGKADSJWCSTI4GDA/graph.json","events_json":"https://pith.science/api/pith-number/PJ7CADNDDTVGKADSJWCSTI4GDA/events.json","paper":"https://pith.science/paper/PJ7CADND"},"agent_actions":{"view_html":"https://pith.science/pith/PJ7CADNDDTVGKADSJWCSTI4GDA","download_json":"https://pith.science/pith/PJ7CADNDDTVGKADSJWCSTI4GDA.json","view_paper":"https://pith.science/paper/PJ7CADND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.05880&json=true","fetch_graph":"https://pith.science/api/pith-number/PJ7CADNDDTVGKADSJWCSTI4GDA/graph.json","fetch_events":"https://pith.science/api/pith-number/PJ7CADNDDTVGKADSJWCSTI4GDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJ7CADNDDTVGKADSJWCSTI4GDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJ7CADNDDTVGKADSJWCSTI4GDA/action/storage_attestation","attest_author":"https://pith.science/pith/PJ7CADNDDTVGKADSJWCSTI4GDA/action/author_attestation","sign_citation":"https://pith.science/pith/PJ7CADNDDTVGKADSJWCSTI4GDA/action/citation_signature","submit_replication":"https://pith.science/pith/PJ7CADNDDTVGKADSJWCSTI4GDA/action/replication_record"}},"created_at":"2026-05-18T00:20:54.456668+00:00","updated_at":"2026-05-18T00:20:54.456668+00:00"}