{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZJVQJLXHUUV25W5CEVM6GUIM4S","short_pith_number":"pith:ZJVQJLXH","schema_version":"1.0","canonical_sha256":"ca6b04aee7a52baedba22559e3510ce4b786d657b0fe9db64d2a468bfdbe7068","source":{"kind":"arxiv","id":"1709.06622","version":1},"attestation_state":"computed","paper":{"title":"Distributed Training Large-Scale Deep Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DC","authors_text":"Cheng-Lung Sung, Chia-Chin Tsao, Chun-Nan Chou, Chun-Yen Chen, Edward Y. Chang, Jui-Lin Wu, Kuan-Chieh Tung, Shang-Xuan Zou, Ting-Wei Lin","submitted_at":"2017-08-10T09:24:27Z","abstract_excerpt":"Scale of data and scale of computation infrastructures together enable the current deep learning renaissance. However, training large-scale deep architectures demands both algorithmic improvement and careful system configuration. In this paper, we focus on employing the system approach to speed up large-scale training. Via lessons learned from our routine benchmarking effort, we first identify bottlenecks and overheads that hinter data parallelism. We then devise guidelines that help practitioners to configure an effective system and fine-tune parameters to achieve desired speedup. Specificall"},"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":"1709.06622","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2017-08-10T09:24:27Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"eb8d1b3e89a69c4ed1f25ec7958af990a25ddb909e6833caaa3326c0a1306f8f","abstract_canon_sha256":"608905910d825b6b6f303d1fba867eec286d555b4a155385bbc12508691a6e64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:40.958630Z","signature_b64":"nkvhGCMdv0DFJwIZDFo07aep+FJqfMLH91w2wVRgiJsY60NRSVSYayGAun2y98/pvH7wws3jLEMLMuEVbDzpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca6b04aee7a52baedba22559e3510ce4b786d657b0fe9db64d2a468bfdbe7068","last_reissued_at":"2026-05-18T00:34:40.957876Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:40.957876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed Training Large-Scale Deep Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DC","authors_text":"Cheng-Lung Sung, Chia-Chin Tsao, Chun-Nan Chou, Chun-Yen Chen, Edward Y. Chang, Jui-Lin Wu, Kuan-Chieh Tung, Shang-Xuan Zou, Ting-Wei Lin","submitted_at":"2017-08-10T09:24:27Z","abstract_excerpt":"Scale of data and scale of computation infrastructures together enable the current deep learning renaissance. However, training large-scale deep architectures demands both algorithmic improvement and careful system configuration. In this paper, we focus on employing the system approach to speed up large-scale training. Via lessons learned from our routine benchmarking effort, we first identify bottlenecks and overheads that hinter data parallelism. We then devise guidelines that help practitioners to configure an effective system and fine-tune parameters to achieve desired speedup. Specificall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06622","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":"1709.06622","created_at":"2026-05-18T00:34:40.958001+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.06622v1","created_at":"2026-05-18T00:34:40.958001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06622","created_at":"2026-05-18T00:34:40.958001+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJVQJLXHUUV2","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJVQJLXHUUV25W5C","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJVQJLXH","created_at":"2026-05-18T12:31:59.375834+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/ZJVQJLXHUUV25W5CEVM6GUIM4S","json":"https://pith.science/pith/ZJVQJLXHUUV25W5CEVM6GUIM4S.json","graph_json":"https://pith.science/api/pith-number/ZJVQJLXHUUV25W5CEVM6GUIM4S/graph.json","events_json":"https://pith.science/api/pith-number/ZJVQJLXHUUV25W5CEVM6GUIM4S/events.json","paper":"https://pith.science/paper/ZJVQJLXH"},"agent_actions":{"view_html":"https://pith.science/pith/ZJVQJLXHUUV25W5CEVM6GUIM4S","download_json":"https://pith.science/pith/ZJVQJLXHUUV25W5CEVM6GUIM4S.json","view_paper":"https://pith.science/paper/ZJVQJLXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.06622&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJVQJLXHUUV25W5CEVM6GUIM4S/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJVQJLXHUUV25W5CEVM6GUIM4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJVQJLXHUUV25W5CEVM6GUIM4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJVQJLXHUUV25W5CEVM6GUIM4S/action/storage_attestation","attest_author":"https://pith.science/pith/ZJVQJLXHUUV25W5CEVM6GUIM4S/action/author_attestation","sign_citation":"https://pith.science/pith/ZJVQJLXHUUV25W5CEVM6GUIM4S/action/citation_signature","submit_replication":"https://pith.science/pith/ZJVQJLXHUUV25W5CEVM6GUIM4S/action/replication_record"}},"created_at":"2026-05-18T00:34:40.958001+00:00","updated_at":"2026-05-18T00:34:40.958001+00:00"}