{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EGWUUQ5OKLETKBJLERGLRKQ6CY","short_pith_number":"pith:EGWUUQ5O","schema_version":"1.0","canonical_sha256":"21ad4a43ae52c935052b244cb8aa1e162fbf69dd394720bef3f5b8a860d268d3","source":{"kind":"arxiv","id":"2111.06171","version":5},"attestation_state":"computed","paper":{"title":"Convergence and Stability of the Stochastic Proximal Point Algorithm with Momentum","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Anastasios Kyrillidis, Junhyung Lyle Kim, Panos Toulis","submitted_at":"2021-11-11T12:17:22Z","abstract_excerpt":"Stochastic gradient descent with momentum (SGDM) is the dominant algorithm in many optimization scenarios, including convex optimization instances and non-convex neural network training. Yet, in the stochastic setting, momentum interferes with gradient noise, often leading to specific step size and momentum choices in order to guarantee convergence, set aside acceleration. Proximal point methods, on the other hand, have gained much attention due to their numerical stability and elasticity against imperfect tuning. Their stochastic accelerated variants though have received limited attention: ho"},"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":"2111.06171","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2021-11-11T12:17:22Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"1ca99ad32cf4bd608bc9353838fe88eef922cd4d04ae9d57fc6bad695296e6c7","abstract_canon_sha256":"7f5b7cd8dc99a9b856cc4e1d8205e806c8a4fdc043fcdec8d889cfd2d9497813"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:43.287663Z","signature_b64":"c6PcUlD2AywvCsOyRIUtSV9viE95lHJo07biukhqxK6RWhlhpQyy9/tv5JZG8VFT73cqmt1T7zluyUZyJs5FDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21ad4a43ae52c935052b244cb8aa1e162fbf69dd394720bef3f5b8a860d268d3","last_reissued_at":"2026-07-05T06:24:43.287169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:43.287169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence and Stability of the Stochastic Proximal Point Algorithm with Momentum","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Anastasios Kyrillidis, Junhyung Lyle Kim, Panos Toulis","submitted_at":"2021-11-11T12:17:22Z","abstract_excerpt":"Stochastic gradient descent with momentum (SGDM) is the dominant algorithm in many optimization scenarios, including convex optimization instances and non-convex neural network training. Yet, in the stochastic setting, momentum interferes with gradient noise, often leading to specific step size and momentum choices in order to guarantee convergence, set aside acceleration. Proximal point methods, on the other hand, have gained much attention due to their numerical stability and elasticity against imperfect tuning. Their stochastic accelerated variants though have received limited attention: ho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.06171","kind":"arxiv","version":5},"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/2111.06171/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":"2111.06171","created_at":"2026-07-05T06:24:43.287230+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.06171v5","created_at":"2026-07-05T06:24:43.287230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.06171","created_at":"2026-07-05T06:24:43.287230+00:00"},{"alias_kind":"pith_short_12","alias_value":"EGWUUQ5OKLET","created_at":"2026-07-05T06:24:43.287230+00:00"},{"alias_kind":"pith_short_16","alias_value":"EGWUUQ5OKLETKBJL","created_at":"2026-07-05T06:24:43.287230+00:00"},{"alias_kind":"pith_short_8","alias_value":"EGWUUQ5O","created_at":"2026-07-05T06:24:43.287230+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EGWUUQ5OKLETKBJLERGLRKQ6CY","json":"https://pith.science/pith/EGWUUQ5OKLETKBJLERGLRKQ6CY.json","graph_json":"https://pith.science/api/pith-number/EGWUUQ5OKLETKBJLERGLRKQ6CY/graph.json","events_json":"https://pith.science/api/pith-number/EGWUUQ5OKLETKBJLERGLRKQ6CY/events.json","paper":"https://pith.science/paper/EGWUUQ5O"},"agent_actions":{"view_html":"https://pith.science/pith/EGWUUQ5OKLETKBJLERGLRKQ6CY","download_json":"https://pith.science/pith/EGWUUQ5OKLETKBJLERGLRKQ6CY.json","view_paper":"https://pith.science/paper/EGWUUQ5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.06171&json=true","fetch_graph":"https://pith.science/api/pith-number/EGWUUQ5OKLETKBJLERGLRKQ6CY/graph.json","fetch_events":"https://pith.science/api/pith-number/EGWUUQ5OKLETKBJLERGLRKQ6CY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EGWUUQ5OKLETKBJLERGLRKQ6CY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EGWUUQ5OKLETKBJLERGLRKQ6CY/action/storage_attestation","attest_author":"https://pith.science/pith/EGWUUQ5OKLETKBJLERGLRKQ6CY/action/author_attestation","sign_citation":"https://pith.science/pith/EGWUUQ5OKLETKBJLERGLRKQ6CY/action/citation_signature","submit_replication":"https://pith.science/pith/EGWUUQ5OKLETKBJLERGLRKQ6CY/action/replication_record"}},"created_at":"2026-07-05T06:24:43.287230+00:00","updated_at":"2026-07-05T06:24:43.287230+00:00"}