{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YGWJQMVEZRBQE66XOS6CD356BL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"82b4e6aa81dd734b0f3566127f903d130e4399074ba28d06a2d5944c769306bb","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-04T03:39:30Z","title_canon_sha256":"d27f3c109e483fa0e48e31a84ddb24d75024501c55cd39a1132858e9221afe6f"},"schema_version":"1.0","source":{"id":"1905.01422","kind":"arxiv","version":8}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.01422","created_at":"2026-07-05T01:33:16Z"},{"alias_kind":"arxiv_version","alias_value":"1905.01422v8","created_at":"2026-07-05T01:33:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01422","created_at":"2026-07-05T01:33:16Z"},{"alias_kind":"pith_short_12","alias_value":"YGWJQMVEZRBQ","created_at":"2026-07-05T01:33:16Z"},{"alias_kind":"pith_short_16","alias_value":"YGWJQMVEZRBQE66X","created_at":"2026-07-05T01:33:16Z"},{"alias_kind":"pith_short_8","alias_value":"YGWJQMVE","created_at":"2026-07-05T01:33:16Z"}],"graph_snapshots":[{"event_id":"sha256:2f6794c105eb5d3fe1dba928f704d0041e1114db331b90d6545e902d120352bb","target":"graph","created_at":"2026-07-05T01:33:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1905.01422/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the remote stochastic gradient (RSG) method, which computes the gradients at configurable remote observation points, in order to improve the convergence rate and suppress gradient noise at the same time for different curvatures. RSG is further combined with adaptive methods to construct ARSG for acceleration. The method is efficient in computation and memory, and is straightforward to implement. We analyze the convergence properties by modeling the training process as a dynamic system, which provides a guideline to select the configurable observation factor without grid search. ARSG","authors_text":"Guangwen Yang, Hao Jing, Liang Qiao, Ouyi Li, Wei Xue, Wenlai Zhao, Yushu Chen, Zhiqiang Liu","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-04T03:39:30Z","title":"An Adaptive Remote Stochastic Gradient Method for Training Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01422","kind":"arxiv","version":8},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:92993be3d392b713a93670a68ade598f8c09792d24e4a4286b4fed13b7fb9d99","target":"record","created_at":"2026-07-05T01:33:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"82b4e6aa81dd734b0f3566127f903d130e4399074ba28d06a2d5944c769306bb","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-04T03:39:30Z","title_canon_sha256":"d27f3c109e483fa0e48e31a84ddb24d75024501c55cd39a1132858e9221afe6f"},"schema_version":"1.0","source":{"id":"1905.01422","kind":"arxiv","version":8}},"canonical_sha256":"c1ac9832a4cc43027bd774bc21efbe0aeca699ad099ceee01ef5e507788d5799","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1ac9832a4cc43027bd774bc21efbe0aeca699ad099ceee01ef5e507788d5799","first_computed_at":"2026-07-05T01:33:16.679606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:33:16.679606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8yAAUj2LbcXaEZQct7BybcEGrbyW6GIhFhWbE8cYhchkelB0yMiXnfed3dsHRw+kJ9sT2sdsrLPfe4cApW0NCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:33:16.680088Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.01422","source_kind":"arxiv","source_version":8}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92993be3d392b713a93670a68ade598f8c09792d24e4a4286b4fed13b7fb9d99","sha256:2f6794c105eb5d3fe1dba928f704d0041e1114db331b90d6545e902d120352bb"],"state_sha256":"577335fa3e6cf412bef6f6fa7ed1604238b50a1373087bc04e696bec16b5b869"}