{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6CKBJDZOKRQ6KJJ2ZVSBU667G4","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":"5360b9e2e51402bff8592e17e0b793692dd18fd0ff98740bb7331a3d427d7260","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-09-29T16:54:53Z","title_canon_sha256":"5f3d11855b34c1fb88a5b34387e21224ba1c29e09bb6612db91fd539a0ad2492"},"schema_version":"1.0","source":{"id":"2209.14937","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14937","created_at":"2026-07-05T06:55:49Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14937v2","created_at":"2026-07-05T06:55:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14937","created_at":"2026-07-05T06:55:49Z"},{"alias_kind":"pith_short_12","alias_value":"6CKBJDZOKRQ6","created_at":"2026-07-05T06:55:49Z"},{"alias_kind":"pith_short_16","alias_value":"6CKBJDZOKRQ6KJJ2","created_at":"2026-07-05T06:55:49Z"},{"alias_kind":"pith_short_8","alias_value":"6CKBJDZO","created_at":"2026-07-05T06:55:49Z"}],"graph_snapshots":[{"event_id":"sha256:d935803f212b9f3300bdab69d70d9509db8fa6d4054683619dfe0b103c528bb8","target":"graph","created_at":"2026-07-05T06:55:49Z","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/2209.14937/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Classical machine learning models such as deep neural networks are usually trained by using Stochastic Gradient Descent-based (SGD) algorithms. The classical SGD can be interpreted as a discretization of the stochastic gradient flow. In this paper we propose a novel, robust and accelerated stochastic optimizer that relies on two key elements: (1) an accelerated Nesterov-like Stochastic Differential Equation (SDE) and (2) its semi-implicit Gauss-Seidel type discretization. The convergence and stability of the obtained method, referred to as NAG-GS, are first studied extensively in the case of t","authors_text":"Aleksandr Katrutsa, Daniel Bershatsky, Daniil Merkulov, Ivan Oseledets, Olga Tsymboi, Valentin Leplat","cross_cats":["cs.LG","cs.NA","math.NA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-09-29T16:54:53Z","title":"NAG-GS: Semi-Implicit, Accelerated and Robust Stochastic Optimizer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14937","kind":"arxiv","version":2},"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":"sha256:21b05bc2645f3c7560fc3b7fc09184bc8169a8b3abbd9ea6bef3a281ec81b011","target":"record","created_at":"2026-07-05T06:55:49Z","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":"5360b9e2e51402bff8592e17e0b793692dd18fd0ff98740bb7331a3d427d7260","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-09-29T16:54:53Z","title_canon_sha256":"5f3d11855b34c1fb88a5b34387e21224ba1c29e09bb6612db91fd539a0ad2492"},"schema_version":"1.0","source":{"id":"2209.14937","kind":"arxiv","version":2}},"canonical_sha256":"f094148f2e5461e5253acd641a7bdf3737a45b6ae5a31fc1e68cf4caa0ccb6c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f094148f2e5461e5253acd641a7bdf3737a45b6ae5a31fc1e68cf4caa0ccb6c2","first_computed_at":"2026-07-05T06:55:49.639987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:55:49.639987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0NjPCOHSz7hrNq07bmROxvCaln6maycdvv3+oi7STLgWy94tmuTf+Y1iMxKmdPCsjYaIsOCQEAiFsFBDKoUsDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:55:49.640500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.14937","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21b05bc2645f3c7560fc3b7fc09184bc8169a8b3abbd9ea6bef3a281ec81b011","sha256:d935803f212b9f3300bdab69d70d9509db8fa6d4054683619dfe0b103c528bb8"],"state_sha256":"438ed7c3fd9c1bcc91f4acef6f9fa5dc710caa44370cbf31493c510f36c671ae"}