{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RQIO63QH7EXVKE27IKEHGN5LL4","short_pith_number":"pith:RQIO63QH","schema_version":"1.0","canonical_sha256":"8c10ef6e07f92f55135f42887337ab5f1d0af824d79eca73ed0891b401ce58d9","source":{"kind":"arxiv","id":"1901.07445","version":2},"attestation_state":"computed","paper":{"title":"Accelerated Linear Convergence of Stochastic Momentum Methods in Wasserstein Distances","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Bugra Can, Lingjiong Zhu, Mert Gurbuzbalaban","submitted_at":"2019-01-22T16:16:42Z","abstract_excerpt":"Momentum methods such as Polyak's heavy ball (HB) method, Nesterov's accelerated gradient (AG) as well as accelerated projected gradient (APG) method have been commonly used in machine learning practice, but their performance is quite sensitive to noise in the gradients. We study these methods under a first-order stochastic oracle model where noisy estimates of the gradients are available. For strongly convex problems, we show that the distribution of the iterates of AG converges with the accelerated $O(\\sqrt{\\kappa}\\log(1/\\varepsilon))$ linear rate to a ball of radius $\\varepsilon$ centered a"},"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":"1901.07445","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-01-22T16:16:42Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"474e3cc094fa6d5da404fe650793f5476ebd05eb3bf5518b983b220f0ffff47c","abstract_canon_sha256":"6275588bdae97829c11d388cb5daa348a08684c4fb42763e922bf364ebc01d04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:06.047276Z","signature_b64":"iMEBhLP/n7rzcA5cq5c7xIR5srYnE+SfNXZfYb/qTiY2F2sS3wIcdoZVmkLauFVia37u1BuNPVrRC/25DsyMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c10ef6e07f92f55135f42887337ab5f1d0af824d79eca73ed0891b401ce58d9","last_reissued_at":"2026-07-04T23:58:06.046934Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:06.046934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerated Linear Convergence of Stochastic Momentum Methods in Wasserstein Distances","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Bugra Can, Lingjiong Zhu, Mert Gurbuzbalaban","submitted_at":"2019-01-22T16:16:42Z","abstract_excerpt":"Momentum methods such as Polyak's heavy ball (HB) method, Nesterov's accelerated gradient (AG) as well as accelerated projected gradient (APG) method have been commonly used in machine learning practice, but their performance is quite sensitive to noise in the gradients. We study these methods under a first-order stochastic oracle model where noisy estimates of the gradients are available. For strongly convex problems, we show that the distribution of the iterates of AG converges with the accelerated $O(\\sqrt{\\kappa}\\log(1/\\varepsilon))$ linear rate to a ball of radius $\\varepsilon$ centered a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07445","kind":"arxiv","version":2},"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/1901.07445/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":"1901.07445","created_at":"2026-07-04T23:58:06.046988+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.07445v2","created_at":"2026-07-04T23:58:06.046988+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07445","created_at":"2026-07-04T23:58:06.046988+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQIO63QH7EXV","created_at":"2026-07-04T23:58:06.046988+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQIO63QH7EXVKE27","created_at":"2026-07-04T23:58:06.046988+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQIO63QH","created_at":"2026-07-04T23:58:06.046988+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/RQIO63QH7EXVKE27IKEHGN5LL4","json":"https://pith.science/pith/RQIO63QH7EXVKE27IKEHGN5LL4.json","graph_json":"https://pith.science/api/pith-number/RQIO63QH7EXVKE27IKEHGN5LL4/graph.json","events_json":"https://pith.science/api/pith-number/RQIO63QH7EXVKE27IKEHGN5LL4/events.json","paper":"https://pith.science/paper/RQIO63QH"},"agent_actions":{"view_html":"https://pith.science/pith/RQIO63QH7EXVKE27IKEHGN5LL4","download_json":"https://pith.science/pith/RQIO63QH7EXVKE27IKEHGN5LL4.json","view_paper":"https://pith.science/paper/RQIO63QH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.07445&json=true","fetch_graph":"https://pith.science/api/pith-number/RQIO63QH7EXVKE27IKEHGN5LL4/graph.json","fetch_events":"https://pith.science/api/pith-number/RQIO63QH7EXVKE27IKEHGN5LL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQIO63QH7EXVKE27IKEHGN5LL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQIO63QH7EXVKE27IKEHGN5LL4/action/storage_attestation","attest_author":"https://pith.science/pith/RQIO63QH7EXVKE27IKEHGN5LL4/action/author_attestation","sign_citation":"https://pith.science/pith/RQIO63QH7EXVKE27IKEHGN5LL4/action/citation_signature","submit_replication":"https://pith.science/pith/RQIO63QH7EXVKE27IKEHGN5LL4/action/replication_record"}},"created_at":"2026-07-04T23:58:06.046988+00:00","updated_at":"2026-07-04T23:58:06.046988+00:00"}