{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4FKSQ6LCRVXGPQY3J3O4PMQ7EZ","short_pith_number":"pith:4FKSQ6LC","schema_version":"1.0","canonical_sha256":"e1552879628d6e67c31b4eddc7b21f2666f4f35187ee58d8aac858fcf2331517","source":{"kind":"arxiv","id":"2305.19259","version":4},"attestation_state":"computed","paper":{"title":"On Convergence of Incremental Gradient for Non-Convex Smooth Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anastasia Koloskova, Martin Jaggi, Nikita Doikov, Sebastian U. Stich","submitted_at":"2023-05-30T17:47:27Z","abstract_excerpt":"In machine learning and neural network optimization, algorithms like incremental gradient, and shuffle SGD are popular due to minimizing the number of cache misses and good practical convergence behavior. However, their optimization properties in theory, especially for non-convex smooth functions, remain incompletely explored.\n  This paper delves into the convergence properties of SGD algorithms with arbitrary data ordering, within a broad framework for non-convex smooth functions. Our findings show enhanced convergence guarantees for incremental gradient and single shuffle SGD. Particularly i"},"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":"2305.19259","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-30T17:47:27Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"38ff8ccb3cbc20db2cf96d738a337783c2b0b094c8086734bb81f99c02815f11","abstract_canon_sha256":"454d9808c0661cfeac32cf9b0024336a98bf053ac792b7eca667e3846fbc9718"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:53.108795Z","signature_b64":"nSOkXjO5YH0j49/UONuBt9lkvG2geJ/Tjjuws0m9n9GU98WBUz8aYSgqIGTYfrxlW6BQD9PkiPdG8yitlOLwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1552879628d6e67c31b4eddc7b21f2666f4f35187ee58d8aac858fcf2331517","last_reissued_at":"2026-07-05T07:43:53.108372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:53.108372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Convergence of Incremental Gradient for Non-Convex Smooth Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anastasia Koloskova, Martin Jaggi, Nikita Doikov, Sebastian U. Stich","submitted_at":"2023-05-30T17:47:27Z","abstract_excerpt":"In machine learning and neural network optimization, algorithms like incremental gradient, and shuffle SGD are popular due to minimizing the number of cache misses and good practical convergence behavior. However, their optimization properties in theory, especially for non-convex smooth functions, remain incompletely explored.\n  This paper delves into the convergence properties of SGD algorithms with arbitrary data ordering, within a broad framework for non-convex smooth functions. Our findings show enhanced convergence guarantees for incremental gradient and single shuffle SGD. Particularly i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19259","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/2305.19259/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":"2305.19259","created_at":"2026-07-05T07:43:53.108432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.19259v4","created_at":"2026-07-05T07:43:53.108432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19259","created_at":"2026-07-05T07:43:53.108432+00:00"},{"alias_kind":"pith_short_12","alias_value":"4FKSQ6LCRVXG","created_at":"2026-07-05T07:43:53.108432+00:00"},{"alias_kind":"pith_short_16","alias_value":"4FKSQ6LCRVXGPQY3","created_at":"2026-07-05T07:43:53.108432+00:00"},{"alias_kind":"pith_short_8","alias_value":"4FKSQ6LC","created_at":"2026-07-05T07:43:53.108432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13434","citing_title":"Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity","ref_index":106,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4FKSQ6LCRVXGPQY3J3O4PMQ7EZ","json":"https://pith.science/pith/4FKSQ6LCRVXGPQY3J3O4PMQ7EZ.json","graph_json":"https://pith.science/api/pith-number/4FKSQ6LCRVXGPQY3J3O4PMQ7EZ/graph.json","events_json":"https://pith.science/api/pith-number/4FKSQ6LCRVXGPQY3J3O4PMQ7EZ/events.json","paper":"https://pith.science/paper/4FKSQ6LC"},"agent_actions":{"view_html":"https://pith.science/pith/4FKSQ6LCRVXGPQY3J3O4PMQ7EZ","download_json":"https://pith.science/pith/4FKSQ6LCRVXGPQY3J3O4PMQ7EZ.json","view_paper":"https://pith.science/paper/4FKSQ6LC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.19259&json=true","fetch_graph":"https://pith.science/api/pith-number/4FKSQ6LCRVXGPQY3J3O4PMQ7EZ/graph.json","fetch_events":"https://pith.science/api/pith-number/4FKSQ6LCRVXGPQY3J3O4PMQ7EZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4FKSQ6LCRVXGPQY3J3O4PMQ7EZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4FKSQ6LCRVXGPQY3J3O4PMQ7EZ/action/storage_attestation","attest_author":"https://pith.science/pith/4FKSQ6LCRVXGPQY3J3O4PMQ7EZ/action/author_attestation","sign_citation":"https://pith.science/pith/4FKSQ6LCRVXGPQY3J3O4PMQ7EZ/action/citation_signature","submit_replication":"https://pith.science/pith/4FKSQ6LCRVXGPQY3J3O4PMQ7EZ/action/replication_record"}},"created_at":"2026-07-05T07:43:53.108432+00:00","updated_at":"2026-07-05T07:43:53.108432+00:00"}