{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JUEYUSQTNP7OCJR3DWKBONVQPY","short_pith_number":"pith:JUEYUSQT","schema_version":"1.0","canonical_sha256":"4d098a4a136bfee1263b1d941736b07e1b00bc970fb1618b058f4d7d59a5b182","source":{"kind":"arxiv","id":"2204.05923","version":4},"attestation_state":"computed","paper":{"title":"An Algebraically Converging Stochastic Gradient Descent Algorithm for Global Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Bj\\\"orn Engquist, Kui Ren, Yunan Yang","submitted_at":"2022-04-12T16:27:49Z","abstract_excerpt":"We propose a new gradient descent algorithm with added stochastic terms for finding the global optimizers of nonconvex optimization problems. A key component in the algorithm is the adaptive tuning of the randomness based on the value of the objective function. In the language of simulated annealing, the temperature is state-dependent. With this, we prove the global convergence of the algorithm with an algebraic rate both in probability and in the parameter space. This is a significant improvement over the classical rate from using a more straightforward control of the noise term. The converge"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2204.05923","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-04-12T16:27:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8b9b4c40b21d2a100975f1c0eb30597394e7c6a098e076c46f1b14af18f9e6ac","abstract_canon_sha256":"d4f0e4238357f2ed61ebb882bb8918b71ddcb418dfc567499b0f99ca5225b40b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:41.798726Z","signature_b64":"y9iywFY1qPCo0jxGUuanay8r4Uwg8wuxm+MR0z6Wk6gQh4voMHng3+9T9J6UgMAIv1M3fR2ZynGNnW7m1b0LBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d098a4a136bfee1263b1d941736b07e1b00bc970fb1618b058f4d7d59a5b182","last_reissued_at":"2026-07-05T11:20:41.798278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:41.798278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Algebraically Converging Stochastic Gradient Descent Algorithm for Global Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Bj\\\"orn Engquist, Kui Ren, Yunan Yang","submitted_at":"2022-04-12T16:27:49Z","abstract_excerpt":"We propose a new gradient descent algorithm with added stochastic terms for finding the global optimizers of nonconvex optimization problems. A key component in the algorithm is the adaptive tuning of the randomness based on the value of the objective function. In the language of simulated annealing, the temperature is state-dependent. With this, we prove the global convergence of the algorithm with an algebraic rate both in probability and in the parameter space. This is a significant improvement over the classical rate from using a more straightforward control of the noise term. The converge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05923","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.05923/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2204.05923","created_at":"2026-07-05T11:20:41.798340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.05923v4","created_at":"2026-07-05T11:20:41.798340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05923","created_at":"2026-07-05T11:20:41.798340+00:00"},{"alias_kind":"pith_short_12","alias_value":"JUEYUSQTNP7O","created_at":"2026-07-05T11:20:41.798340+00:00"},{"alias_kind":"pith_short_16","alias_value":"JUEYUSQTNP7OCJR3","created_at":"2026-07-05T11:20:41.798340+00:00"},{"alias_kind":"pith_short_8","alias_value":"JUEYUSQT","created_at":"2026-07-05T11:20:41.798340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15220","citing_title":"Sampling with Adaptive Variance for Multimodal Distributions","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JUEYUSQTNP7OCJR3DWKBONVQPY","json":"https://pith.science/pith/JUEYUSQTNP7OCJR3DWKBONVQPY.json","graph_json":"https://pith.science/api/pith-number/JUEYUSQTNP7OCJR3DWKBONVQPY/graph.json","events_json":"https://pith.science/api/pith-number/JUEYUSQTNP7OCJR3DWKBONVQPY/events.json","paper":"https://pith.science/paper/JUEYUSQT"},"agent_actions":{"view_html":"https://pith.science/pith/JUEYUSQTNP7OCJR3DWKBONVQPY","download_json":"https://pith.science/pith/JUEYUSQTNP7OCJR3DWKBONVQPY.json","view_paper":"https://pith.science/paper/JUEYUSQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.05923&json=true","fetch_graph":"https://pith.science/api/pith-number/JUEYUSQTNP7OCJR3DWKBONVQPY/graph.json","fetch_events":"https://pith.science/api/pith-number/JUEYUSQTNP7OCJR3DWKBONVQPY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JUEYUSQTNP7OCJR3DWKBONVQPY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JUEYUSQTNP7OCJR3DWKBONVQPY/action/storage_attestation","attest_author":"https://pith.science/pith/JUEYUSQTNP7OCJR3DWKBONVQPY/action/author_attestation","sign_citation":"https://pith.science/pith/JUEYUSQTNP7OCJR3DWKBONVQPY/action/citation_signature","submit_replication":"https://pith.science/pith/JUEYUSQTNP7OCJR3DWKBONVQPY/action/replication_record"}},"created_at":"2026-07-05T11:20:41.798340+00:00","updated_at":"2026-07-05T11:20:41.798340+00:00"}