{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WPWUWXDM2JF6OKJSNAAPJ6MVAW","short_pith_number":"pith:WPWUWXDM","schema_version":"1.0","canonical_sha256":"b3ed4b5c6cd24be729326800f4f9950594b03fec59fc00e2d5e52b03d4ad4fb4","source":{"kind":"arxiv","id":"1810.11787","version":1},"attestation_state":"computed","paper":{"title":"A Hitchhiker's Guide On Distributed Training of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Karanbir Chahal, Kuntal Dey, Manraj Singh Grover","submitted_at":"2018-10-28T09:37:47Z","abstract_excerpt":"Deep learning has led to tremendous advancements in the field of Artificial Intelligence. One caveat however is the substantial amount of compute needed to train these deep learning models. Training a benchmark dataset like ImageNet on a single machine with a modern GPU can take upto a week, distributing training on multiple machines has been observed to drastically bring this time down. Recent work has brought down ImageNet training time to a time as low as 4 minutes by using a cluster of 2048 GPUs. This paper surveys the various algorithms and techniques used to distribute training and prese"},"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":"1810.11787","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-28T09:37:47Z","cross_cats_sorted":["cs.AI","cs.DC","stat.ML"],"title_canon_sha256":"870b6ff473781b144825b5ff36cd4716fcf056e86d82edab08c92c0383d5cabe","abstract_canon_sha256":"450dd14575a4860411bcb5489a7a6509b965c08fcabaec6a5c895ba64c836248"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:07.391807Z","signature_b64":"FfbeAWc3JSOmCoQ9oq044Dw4mhm32YFw78FJKmdSJVMP6pi4TO86zsfn3qT8jUBTh/2qCT9z9vXhQH1Sg673Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3ed4b5c6cd24be729326800f4f9950594b03fec59fc00e2d5e52b03d4ad4fb4","last_reissued_at":"2026-05-18T00:02:07.391028Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:07.391028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hitchhiker's Guide On Distributed Training of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Karanbir Chahal, Kuntal Dey, Manraj Singh Grover","submitted_at":"2018-10-28T09:37:47Z","abstract_excerpt":"Deep learning has led to tremendous advancements in the field of Artificial Intelligence. One caveat however is the substantial amount of compute needed to train these deep learning models. Training a benchmark dataset like ImageNet on a single machine with a modern GPU can take upto a week, distributing training on multiple machines has been observed to drastically bring this time down. Recent work has brought down ImageNet training time to a time as low as 4 minutes by using a cluster of 2048 GPUs. This paper surveys the various algorithms and techniques used to distribute training and prese"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11787","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":"1810.11787","created_at":"2026-05-18T00:02:07.391155+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.11787v1","created_at":"2026-05-18T00:02:07.391155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11787","created_at":"2026-05-18T00:02:07.391155+00:00"},{"alias_kind":"pith_short_12","alias_value":"WPWUWXDM2JF6","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"WPWUWXDM2JF6OKJS","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"WPWUWXDM","created_at":"2026-05-18T12:33:01.666342+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/WPWUWXDM2JF6OKJSNAAPJ6MVAW","json":"https://pith.science/pith/WPWUWXDM2JF6OKJSNAAPJ6MVAW.json","graph_json":"https://pith.science/api/pith-number/WPWUWXDM2JF6OKJSNAAPJ6MVAW/graph.json","events_json":"https://pith.science/api/pith-number/WPWUWXDM2JF6OKJSNAAPJ6MVAW/events.json","paper":"https://pith.science/paper/WPWUWXDM"},"agent_actions":{"view_html":"https://pith.science/pith/WPWUWXDM2JF6OKJSNAAPJ6MVAW","download_json":"https://pith.science/pith/WPWUWXDM2JF6OKJSNAAPJ6MVAW.json","view_paper":"https://pith.science/paper/WPWUWXDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.11787&json=true","fetch_graph":"https://pith.science/api/pith-number/WPWUWXDM2JF6OKJSNAAPJ6MVAW/graph.json","fetch_events":"https://pith.science/api/pith-number/WPWUWXDM2JF6OKJSNAAPJ6MVAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WPWUWXDM2JF6OKJSNAAPJ6MVAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WPWUWXDM2JF6OKJSNAAPJ6MVAW/action/storage_attestation","attest_author":"https://pith.science/pith/WPWUWXDM2JF6OKJSNAAPJ6MVAW/action/author_attestation","sign_citation":"https://pith.science/pith/WPWUWXDM2JF6OKJSNAAPJ6MVAW/action/citation_signature","submit_replication":"https://pith.science/pith/WPWUWXDM2JF6OKJSNAAPJ6MVAW/action/replication_record"}},"created_at":"2026-05-18T00:02:07.391155+00:00","updated_at":"2026-05-18T00:02:07.391155+00:00"}