{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SL4QW3676GJ3LELMF77HFVFBKM","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":"e0b42b9d33243ea01c30442bce915e85d94e035be131e45aa0663316ffb3be99","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-06-20T14:07:39Z","title_canon_sha256":"56456f78f0f501cad79a3d2e98695436597842624953320d26da1de2deadfab0"},"schema_version":"1.0","source":{"id":"2406.14340","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14340","created_at":"2026-07-05T08:34:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14340v1","created_at":"2026-07-05T08:34:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14340","created_at":"2026-07-05T08:34:49Z"},{"alias_kind":"pith_short_12","alias_value":"SL4QW3676GJ3","created_at":"2026-07-05T08:34:49Z"},{"alias_kind":"pith_short_16","alias_value":"SL4QW3676GJ3LELM","created_at":"2026-07-05T08:34:49Z"},{"alias_kind":"pith_short_8","alias_value":"SL4QW367","created_at":"2026-07-05T08:34:49Z"}],"graph_snapshots":[{"event_id":"sha256:6a2172821221bd98800f064897cef2e4ab1353da54b52efb464613ed989b08ff","target":"graph","created_at":"2026-07-05T08:34:49Z","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/2406.14340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is known that the standard stochastic gradient descent (SGD) optimization method, as well as accelerated and adaptive SGD optimization methods such as the Adam optimizer fail to converge if the learning rates do not converge to zero (as, for example, in the situation of constant learning rates). Numerical simulations often use human-tuned deterministic learning rate schedules or small constant learning rates. The default learning rate schedules for SGD optimization methods in machine learning implementation frameworks such as TensorFlow and Pytorch are constant learning rates. In this work ","authors_text":"Adrian Riekert, Arnulf Jentzen, Steffen Dereich","cross_cats":["cs.LG","cs.NA","math.NA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-06-20T14:07:39Z","title":"Learning rate adaptive stochastic gradient descent optimization methods: numerical simulations for deep learning methods for partial differential equations and convergence analyses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14340","kind":"arxiv","version":1},"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":"sha256:0deddc6f16085d1d0bd427e03f9f53e070b52817021c4f7f175eb0f131bd7f4a","target":"record","created_at":"2026-07-05T08:34:49Z","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":"e0b42b9d33243ea01c30442bce915e85d94e035be131e45aa0663316ffb3be99","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-06-20T14:07:39Z","title_canon_sha256":"56456f78f0f501cad79a3d2e98695436597842624953320d26da1de2deadfab0"},"schema_version":"1.0","source":{"id":"2406.14340","kind":"arxiv","version":1}},"canonical_sha256":"92f90b6fdff193b5916c2ffe72d4a1533c75206bfbed0c4902971376c1eb8345","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92f90b6fdff193b5916c2ffe72d4a1533c75206bfbed0c4902971376c1eb8345","first_computed_at":"2026-07-05T08:34:49.466151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:49.466151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0b2IOG1C/gAOadYR54yvj5bRyvfv/Ei5YU2OS5K2+PVCgYssgIQPoKxh46XXs6NSWdwo4w8yu6Z08yX/ROCLDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:49.466600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.14340","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0deddc6f16085d1d0bd427e03f9f53e070b52817021c4f7f175eb0f131bd7f4a","sha256:6a2172821221bd98800f064897cef2e4ab1353da54b52efb464613ed989b08ff"],"state_sha256":"f228b88aaae72466872fd501311f1bb82c477dcde50c4d9459c944515e7a2ad7"}