{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QVHHWI6SCO2GA4A5L4C5DPEYFM","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":"c3413ae968d014829a598e70a88acb0647f17abd6611186843c3113fd3faddf6","cross_cats_sorted":["cs.LG","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2021-03-08T17:06:18Z","title_canon_sha256":"997662b1cb9b3b4d8e0346682533b099033ee7bb1ae4b3c7603c44c1fcc0719e"},"schema_version":"1.0","source":{"id":"2103.04902","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.04902","created_at":"2026-07-05T04:06:41Z"},{"alias_kind":"arxiv_version","alias_value":"2103.04902v2","created_at":"2026-07-05T04:06:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.04902","created_at":"2026-07-05T04:06:41Z"},{"alias_kind":"pith_short_12","alias_value":"QVHHWI6SCO2G","created_at":"2026-07-05T04:06:41Z"},{"alias_kind":"pith_short_16","alias_value":"QVHHWI6SCO2GA4A5","created_at":"2026-07-05T04:06:41Z"},{"alias_kind":"pith_short_8","alias_value":"QVHHWI6S","created_at":"2026-07-05T04:06:41Z"}],"graph_snapshots":[{"event_id":"sha256:f499b775906789427f6acf9479d3ad3d0474cf0231042eba6165cf7a4ceecdf7","target":"graph","created_at":"2026-07-05T04:06:41Z","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/2103.04902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we investigate how gradient-based algorithms such as gradient descent, (multi-pass) stochastic gradient descent, its persistent variant, and the Langevin algorithm navigate non-convex loss-landscapes and which of them is able to reach the best generalization error at limited sample complexity. We consider the loss landscape of the high-dimensional phase retrieval problem as a prototypical highly non-convex example. We observe that for phase retrieval the stochastic variants of gradient descent are able to reach perfect generalization for regions of control parameters where the gr","authors_text":"Francesca Mignacco, Lenka Zdeborov\\'a, Pierfrancesco Urbani","cross_cats":["cs.LG","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2021-03-08T17:06:18Z","title":"Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.04902","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":"sha256:2c6d9300cb37579377ea859414bc1e72ea6cee88c61d3d7b46e822f4dca44f32","target":"record","created_at":"2026-07-05T04:06:41Z","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":"c3413ae968d014829a598e70a88acb0647f17abd6611186843c3113fd3faddf6","cross_cats_sorted":["cs.LG","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2021-03-08T17:06:18Z","title_canon_sha256":"997662b1cb9b3b4d8e0346682533b099033ee7bb1ae4b3c7603c44c1fcc0719e"},"schema_version":"1.0","source":{"id":"2103.04902","kind":"arxiv","version":2}},"canonical_sha256":"854e7b23d213b460701d5f05d1bc982b1d386865b4ab3678c4371dc628973c09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"854e7b23d213b460701d5f05d1bc982b1d386865b4ab3678c4371dc628973c09","first_computed_at":"2026-07-05T04:06:41.415930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:41.415930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hBLTypamYVKJtMFOB+IoRQU1nNSg+oqsgZCfguQpxo28JYeeumP7d4YANQmgpDQ0ttHiAyN2XeVUA/G2loctCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:41.416360Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.04902","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c6d9300cb37579377ea859414bc1e72ea6cee88c61d3d7b46e822f4dca44f32","sha256:f499b775906789427f6acf9479d3ad3d0474cf0231042eba6165cf7a4ceecdf7"],"state_sha256":"c78626e4c03253174a8c2bdeba65a4a3e1a7a060e5d6bf767c2fc4e5b0f37122"}