{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5KDARQNDDYME4KO7AJIJ4ADESI","short_pith_number":"pith:5KDARQND","schema_version":"1.0","canonical_sha256":"ea8608c1a31e184e29df02509e00649213a001c9827f22658c84e59cd5fa5f9b","source":{"kind":"arxiv","id":"2004.10856","version":1},"attestation_state":"computed","paper":{"title":"TensorOpt: Exploring the Tradeoffs in Distributed DNN Training with Auto-Parallelism","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DC","authors_text":"Fan Yu, James Cheng, Kaihao Ma, Teng Su, Xiao Yan, Yidi Wu, Yuzhen Huang, Zhenkun Cai","submitted_at":"2020-04-16T02:57:35Z","abstract_excerpt":"A good parallelization strategy can significantly improve the efficiency or reduce the cost for the distributed training of deep neural networks (DNNs). Recently, several methods have been proposed to find efficient parallelization strategies but they all optimize a single objective (e.g., execution time, memory consumption) and produce only one strategy. We propose FT, an efficient algorithm that searches for an optimal set of parallelization strategies to allow the trade-off among different objectives. FT can adapt to different scenarios by minimizing the memory consumption when the number o"},"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":"2004.10856","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2020-04-16T02:57:35Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"46315bf5e1c474bfc7246132d1943607587c8553be31c8e8b4794b49d19f096d","abstract_canon_sha256":"57dee4b0438b705ba98db93d258f15337cf1a4db22c483feeb29901f918018f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:47:12.281095Z","signature_b64":"FofQpVxfYXDpqtJ1/p2oyIvHhcYsNKlB36HHYrNAHBXOnBA2QnmBuP4l8RC/FrkB4XlJZBPD+bEVPpdepzgFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea8608c1a31e184e29df02509e00649213a001c9827f22658c84e59cd5fa5f9b","last_reissued_at":"2026-07-05T03:47:12.280689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:47:12.280689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TensorOpt: Exploring the Tradeoffs in Distributed DNN Training with Auto-Parallelism","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DC","authors_text":"Fan Yu, James Cheng, Kaihao Ma, Teng Su, Xiao Yan, Yidi Wu, Yuzhen Huang, Zhenkun Cai","submitted_at":"2020-04-16T02:57:35Z","abstract_excerpt":"A good parallelization strategy can significantly improve the efficiency or reduce the cost for the distributed training of deep neural networks (DNNs). Recently, several methods have been proposed to find efficient parallelization strategies but they all optimize a single objective (e.g., execution time, memory consumption) and produce only one strategy. We propose FT, an efficient algorithm that searches for an optimal set of parallelization strategies to allow the trade-off among different objectives. FT can adapt to different scenarios by minimizing the memory consumption when the number o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.10856","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.10856/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":"2004.10856","created_at":"2026-07-05T03:47:12.280747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.10856v1","created_at":"2026-07-05T03:47:12.280747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.10856","created_at":"2026-07-05T03:47:12.280747+00:00"},{"alias_kind":"pith_short_12","alias_value":"5KDARQNDDYME","created_at":"2026-07-05T03:47:12.280747+00:00"},{"alias_kind":"pith_short_16","alias_value":"5KDARQNDDYME4KO7","created_at":"2026-07-05T03:47:12.280747+00:00"},{"alias_kind":"pith_short_8","alias_value":"5KDARQND","created_at":"2026-07-05T03:47:12.280747+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/5KDARQNDDYME4KO7AJIJ4ADESI","json":"https://pith.science/pith/5KDARQNDDYME4KO7AJIJ4ADESI.json","graph_json":"https://pith.science/api/pith-number/5KDARQNDDYME4KO7AJIJ4ADESI/graph.json","events_json":"https://pith.science/api/pith-number/5KDARQNDDYME4KO7AJIJ4ADESI/events.json","paper":"https://pith.science/paper/5KDARQND"},"agent_actions":{"view_html":"https://pith.science/pith/5KDARQNDDYME4KO7AJIJ4ADESI","download_json":"https://pith.science/pith/5KDARQNDDYME4KO7AJIJ4ADESI.json","view_paper":"https://pith.science/paper/5KDARQND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.10856&json=true","fetch_graph":"https://pith.science/api/pith-number/5KDARQNDDYME4KO7AJIJ4ADESI/graph.json","fetch_events":"https://pith.science/api/pith-number/5KDARQNDDYME4KO7AJIJ4ADESI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5KDARQNDDYME4KO7AJIJ4ADESI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5KDARQNDDYME4KO7AJIJ4ADESI/action/storage_attestation","attest_author":"https://pith.science/pith/5KDARQNDDYME4KO7AJIJ4ADESI/action/author_attestation","sign_citation":"https://pith.science/pith/5KDARQNDDYME4KO7AJIJ4ADESI/action/citation_signature","submit_replication":"https://pith.science/pith/5KDARQNDDYME4KO7AJIJ4ADESI/action/replication_record"}},"created_at":"2026-07-05T03:47:12.280747+00:00","updated_at":"2026-07-05T03:47:12.280747+00:00"}