{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BUMDBEGEY6VDZ2HEB246UOEKEY","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":"452fd71e6646cdded1b64b314b882ea6c0de5af90fbc3a04b8a9953f95e4609b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-07-05T08:53:06Z","title_canon_sha256":"1bbfdef31bab1b0bc9c9ed94734819953b1f2bcd667c9e8239b947bab43a7d33"},"schema_version":"1.0","source":{"id":"2407.04358","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04358","created_at":"2026-07-05T08:40:32Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04358v1","created_at":"2026-07-05T08:40:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04358","created_at":"2026-07-05T08:40:32Z"},{"alias_kind":"pith_short_12","alias_value":"BUMDBEGEY6VD","created_at":"2026-07-05T08:40:32Z"},{"alias_kind":"pith_short_16","alias_value":"BUMDBEGEY6VDZ2HE","created_at":"2026-07-05T08:40:32Z"},{"alias_kind":"pith_short_8","alias_value":"BUMDBEGE","created_at":"2026-07-05T08:40:32Z"}],"graph_snapshots":[{"event_id":"sha256:04f66d01a0632bf59b9085ae4654190ba4e4874811f52f17020bfabd5ad08504","target":"graph","created_at":"2026-07-05T08:40:32Z","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/2407.04358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of minimizing the average of a large number of smooth but possibly non-convex functions. In the context of most machine learning applications, each loss function is non-negative and thus can be expressed as the composition of a square and its real-valued square root. This reformulation allows us to apply the Gauss-Newton method, or the Levenberg-Marquardt method when adding a quadratic regularization. The resulting algorithm, while being computationally as efficient as the vanilla stochastic gradient method, is highly adaptive and can automatically warmup and decay the ","authors_text":"Antonio Orvieto, Lin Xiao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-07-05T08:53:06Z","title":"An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04358","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:c6390d2eb0d9bfa51040e5f060a9925001e5adf8980a2962be06549535c6b496","target":"record","created_at":"2026-07-05T08:40:32Z","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":"452fd71e6646cdded1b64b314b882ea6c0de5af90fbc3a04b8a9953f95e4609b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-07-05T08:53:06Z","title_canon_sha256":"1bbfdef31bab1b0bc9c9ed94734819953b1f2bcd667c9e8239b947bab43a7d33"},"schema_version":"1.0","source":{"id":"2407.04358","kind":"arxiv","version":1}},"canonical_sha256":"0d183090c4c7aa3ce8e40eb9ea388a2627cbbb315a1618eb9ac27a0ec44ef32a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d183090c4c7aa3ce8e40eb9ea388a2627cbbb315a1618eb9ac27a0ec44ef32a","first_computed_at":"2026-07-05T08:40:32.854703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:40:32.854703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ysImz7PfBZXmgmjO3OzrYhIiXM5kLBMdYS04CppllzHv6BwnGDI/XXVTH506bhQA2E620T+J7rHmpEu5VB4wBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:40:32.855150Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04358","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6390d2eb0d9bfa51040e5f060a9925001e5adf8980a2962be06549535c6b496","sha256:04f66d01a0632bf59b9085ae4654190ba4e4874811f52f17020bfabd5ad08504"],"state_sha256":"f1e92a7441695d99f9bfc65d69564a372738b2e33e73f1600330308a980d0357"}