{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XTUXCYZOJZFLQ46IXGBK5OFVCF","short_pith_number":"pith:XTUXCYZO","schema_version":"1.0","canonical_sha256":"bce971632e4e4ab873c8b982aeb8b5115e2563ef875dd16a01896e382c3de10e","source":{"kind":"arxiv","id":"1805.02991","version":1},"attestation_state":"computed","paper":{"title":"Differential Equations for Modeling Asynchronous Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Li He, Qi Meng, Tie-Yan Liu, Wei Chen, Zhi-Ming Ma","submitted_at":"2018-05-08T13:06:26Z","abstract_excerpt":"Asynchronous stochastic gradient descent (ASGD) is a popular parallel optimization algorithm in machine learning. Most theoretical analysis on ASGD take a discrete view and prove upper bounds for their convergence rates. However, the discrete view has its intrinsic limitations: there is no characterization of the optimization path and the proof techniques are induction-based and thus usually complicated. Inspired by the recent successful adoptions of stochastic differential equations (SDE) to the theoretical analysis of SGD, in this paper, we study the continuous approximation of ASGD by using"},"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":"1805.02991","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-08T13:06:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e881b0933ea042d31bf169fc7b2aca4d5ee8d068cd1b5b09af3b8b05063e3c45","abstract_canon_sha256":"b9fadbde3ee1adae423e141aa1f7cd7eb689c46bbcf62a65390e4abaa056702c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:34.980792Z","signature_b64":"LtVU/E77JH4gEFBwvq2J/x9jl5XkOE0C77eukIll5nubng3xW71dz6is/ImOCzXnGMqkoy81FaIZVq30gp0eAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bce971632e4e4ab873c8b982aeb8b5115e2563ef875dd16a01896e382c3de10e","last_reissued_at":"2026-05-18T00:16:34.980029Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:34.980029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differential Equations for Modeling Asynchronous Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Li He, Qi Meng, Tie-Yan Liu, Wei Chen, Zhi-Ming Ma","submitted_at":"2018-05-08T13:06:26Z","abstract_excerpt":"Asynchronous stochastic gradient descent (ASGD) is a popular parallel optimization algorithm in machine learning. Most theoretical analysis on ASGD take a discrete view and prove upper bounds for their convergence rates. However, the discrete view has its intrinsic limitations: there is no characterization of the optimization path and the proof techniques are induction-based and thus usually complicated. Inspired by the recent successful adoptions of stochastic differential equations (SDE) to the theoretical analysis of SGD, in this paper, we study the continuous approximation of ASGD by using"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.02991","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":"1805.02991","created_at":"2026-05-18T00:16:34.980162+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.02991v1","created_at":"2026-05-18T00:16:34.980162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.02991","created_at":"2026-05-18T00:16:34.980162+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTUXCYZOJZFL","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTUXCYZOJZFLQ46I","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTUXCYZO","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/XTUXCYZOJZFLQ46IXGBK5OFVCF","json":"https://pith.science/pith/XTUXCYZOJZFLQ46IXGBK5OFVCF.json","graph_json":"https://pith.science/api/pith-number/XTUXCYZOJZFLQ46IXGBK5OFVCF/graph.json","events_json":"https://pith.science/api/pith-number/XTUXCYZOJZFLQ46IXGBK5OFVCF/events.json","paper":"https://pith.science/paper/XTUXCYZO"},"agent_actions":{"view_html":"https://pith.science/pith/XTUXCYZOJZFLQ46IXGBK5OFVCF","download_json":"https://pith.science/pith/XTUXCYZOJZFLQ46IXGBK5OFVCF.json","view_paper":"https://pith.science/paper/XTUXCYZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.02991&json=true","fetch_graph":"https://pith.science/api/pith-number/XTUXCYZOJZFLQ46IXGBK5OFVCF/graph.json","fetch_events":"https://pith.science/api/pith-number/XTUXCYZOJZFLQ46IXGBK5OFVCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTUXCYZOJZFLQ46IXGBK5OFVCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTUXCYZOJZFLQ46IXGBK5OFVCF/action/storage_attestation","attest_author":"https://pith.science/pith/XTUXCYZOJZFLQ46IXGBK5OFVCF/action/author_attestation","sign_citation":"https://pith.science/pith/XTUXCYZOJZFLQ46IXGBK5OFVCF/action/citation_signature","submit_replication":"https://pith.science/pith/XTUXCYZOJZFLQ46IXGBK5OFVCF/action/replication_record"}},"created_at":"2026-05-18T00:16:34.980162+00:00","updated_at":"2026-05-18T00:16:34.980162+00:00"}