{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IIMELIUJXNL75H34KSTDFS6TL6","short_pith_number":"pith:IIMELIUJ","schema_version":"1.0","canonical_sha256":"421845a289bb57fe9f7c54a632cbd35f8919d06e571264186093096ae41facbe","source":{"kind":"arxiv","id":"2306.03626","version":1},"attestation_state":"computed","paper":{"title":"Understanding Progressive Training Through the Framework of Randomized Coordinate Descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Elnur Gasanov, Peter Richt\\'arik, Rafa{\\l} Szlendak","submitted_at":"2023-06-06T12:27:54Z","abstract_excerpt":"We propose a Randomized Progressive Training algorithm (RPT) -- a stochastic proxy for the well-known Progressive Training method (PT) (Karras et al., 2017). Originally designed to train GANs (Goodfellow et al., 2014), PT was proposed as a heuristic, with no convergence analysis even for the simplest objective functions. On the contrary, to the best of our knowledge, RPT is the first PT-type algorithm with rigorous and sound theoretical guarantees for general smooth objective functions. We cast our method into the established framework of Randomized Coordinate Descent (RCD) (Nesterov, 2012; Ri"},"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":"2306.03626","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-06T12:27:54Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"39566a00738cbf971ae98306e7ad1c1bb8883906b2dac92c90f959c8905b62cd","abstract_canon_sha256":"d6630cc204d56bf6a09c62b088c8b22d07d3ccab0bde67a50a2c2a811a962295"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:00.385868Z","signature_b64":"KKxwYtFZZFHrwfzxWRQsFvbLvkMwUXFQx5iCLYERgENH94ijPIaHh9sLaIz6EnkZ6SjJPgYPinqCkzw7Qs1hAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"421845a289bb57fe9f7c54a632cbd35f8919d06e571264186093096ae41facbe","last_reissued_at":"2026-07-05T06:18:00.385380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:00.385380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Progressive Training Through the Framework of Randomized Coordinate Descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Elnur Gasanov, Peter Richt\\'arik, Rafa{\\l} Szlendak","submitted_at":"2023-06-06T12:27:54Z","abstract_excerpt":"We propose a Randomized Progressive Training algorithm (RPT) -- a stochastic proxy for the well-known Progressive Training method (PT) (Karras et al., 2017). Originally designed to train GANs (Goodfellow et al., 2014), PT was proposed as a heuristic, with no convergence analysis even for the simplest objective functions. On the contrary, to the best of our knowledge, RPT is the first PT-type algorithm with rigorous and sound theoretical guarantees for general smooth objective functions. We cast our method into the established framework of Randomized Coordinate Descent (RCD) (Nesterov, 2012; Ri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03626","kind":"arxiv","version":1},"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/2306.03626/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":"2306.03626","created_at":"2026-07-05T06:18:00.385441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.03626v1","created_at":"2026-07-05T06:18:00.385441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03626","created_at":"2026-07-05T06:18:00.385441+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIMELIUJXNL7","created_at":"2026-07-05T06:18:00.385441+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIMELIUJXNL75H34","created_at":"2026-07-05T06:18:00.385441+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIMELIUJ","created_at":"2026-07-05T06:18:00.385441+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/IIMELIUJXNL75H34KSTDFS6TL6","json":"https://pith.science/pith/IIMELIUJXNL75H34KSTDFS6TL6.json","graph_json":"https://pith.science/api/pith-number/IIMELIUJXNL75H34KSTDFS6TL6/graph.json","events_json":"https://pith.science/api/pith-number/IIMELIUJXNL75H34KSTDFS6TL6/events.json","paper":"https://pith.science/paper/IIMELIUJ"},"agent_actions":{"view_html":"https://pith.science/pith/IIMELIUJXNL75H34KSTDFS6TL6","download_json":"https://pith.science/pith/IIMELIUJXNL75H34KSTDFS6TL6.json","view_paper":"https://pith.science/paper/IIMELIUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.03626&json=true","fetch_graph":"https://pith.science/api/pith-number/IIMELIUJXNL75H34KSTDFS6TL6/graph.json","fetch_events":"https://pith.science/api/pith-number/IIMELIUJXNL75H34KSTDFS6TL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIMELIUJXNL75H34KSTDFS6TL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIMELIUJXNL75H34KSTDFS6TL6/action/storage_attestation","attest_author":"https://pith.science/pith/IIMELIUJXNL75H34KSTDFS6TL6/action/author_attestation","sign_citation":"https://pith.science/pith/IIMELIUJXNL75H34KSTDFS6TL6/action/citation_signature","submit_replication":"https://pith.science/pith/IIMELIUJXNL75H34KSTDFS6TL6/action/replication_record"}},"created_at":"2026-07-05T06:18:00.385441+00:00","updated_at":"2026-07-05T06:18:00.385441+00:00"}