{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IGDYUUQOBNVRQUZR6MYUYMPTGX","short_pith_number":"pith:IGDYUUQO","schema_version":"1.0","canonical_sha256":"41878a520e0b6b185331f3314c31f335e804476897945092f374682ec49702ad","source":{"kind":"arxiv","id":"2312.01047","version":3},"attestation_state":"computed","paper":{"title":"A New Random Reshuffling Method for Nonsmooth Nonconvex Finite-sum Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Andre Milzarek, Junwen Qiu, Xiao Li","submitted_at":"2023-12-02T07:12:00Z","abstract_excerpt":"Random reshuffling techniques are prevalent in large-scale applications, such as training neural networks. While the convergence and acceleration effects of random reshuffling-type methods are fairly well understood in the smooth setting, much less studies seem available in the nonsmooth case. In this work, we design a new normal map-based proximal random reshuffling (norm-PRR) method for nonsmooth nonconvex finite-sum problems. We show that norm-PRR achieves the iteration complexity ${\\cal O}(n^{-1/3}T^{-2/3})$ where $n$ denotes the number of component functions $f(\\cdot,i)$ and $T$ counts th"},"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":"2312.01047","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-12-02T07:12:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d7954508fcd7f80ee0e242aaf23a95600e5d8a83086ca76bc5e172fd4c156420","abstract_canon_sha256":"0a4044fd70fb4082f534a88f45955c082f158a95a0e78e082a3bf88f93c3191d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:53.740737Z","signature_b64":"Tnp1T+H/nbpwaQGrNsZcrfcwNRDEcLioxE/6ZHGyVNxc8h7EeomcuMJPeCFRReF+u/jjMqBV1DafmvhC/BDoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41878a520e0b6b185331f3314c31f335e804476897945092f374682ec49702ad","last_reissued_at":"2026-07-05T11:43:53.740283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:53.740283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A New Random Reshuffling Method for Nonsmooth Nonconvex Finite-sum Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Andre Milzarek, Junwen Qiu, Xiao Li","submitted_at":"2023-12-02T07:12:00Z","abstract_excerpt":"Random reshuffling techniques are prevalent in large-scale applications, such as training neural networks. While the convergence and acceleration effects of random reshuffling-type methods are fairly well understood in the smooth setting, much less studies seem available in the nonsmooth case. In this work, we design a new normal map-based proximal random reshuffling (norm-PRR) method for nonsmooth nonconvex finite-sum problems. We show that norm-PRR achieves the iteration complexity ${\\cal O}(n^{-1/3}T^{-2/3})$ where $n$ denotes the number of component functions $f(\\cdot,i)$ and $T$ counts th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01047","kind":"arxiv","version":3},"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/2312.01047/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":"2312.01047","created_at":"2026-07-05T11:43:53.740345+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.01047v3","created_at":"2026-07-05T11:43:53.740345+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01047","created_at":"2026-07-05T11:43:53.740345+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGDYUUQOBNVR","created_at":"2026-07-05T11:43:53.740345+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGDYUUQOBNVRQUZR","created_at":"2026-07-05T11:43:53.740345+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGDYUUQO","created_at":"2026-07-05T11:43:53.740345+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.13054","citing_title":"Distributed Normal Map-based Stochastic Proximal Gradient Methods over Networks","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IGDYUUQOBNVRQUZR6MYUYMPTGX","json":"https://pith.science/pith/IGDYUUQOBNVRQUZR6MYUYMPTGX.json","graph_json":"https://pith.science/api/pith-number/IGDYUUQOBNVRQUZR6MYUYMPTGX/graph.json","events_json":"https://pith.science/api/pith-number/IGDYUUQOBNVRQUZR6MYUYMPTGX/events.json","paper":"https://pith.science/paper/IGDYUUQO"},"agent_actions":{"view_html":"https://pith.science/pith/IGDYUUQOBNVRQUZR6MYUYMPTGX","download_json":"https://pith.science/pith/IGDYUUQOBNVRQUZR6MYUYMPTGX.json","view_paper":"https://pith.science/paper/IGDYUUQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.01047&json=true","fetch_graph":"https://pith.science/api/pith-number/IGDYUUQOBNVRQUZR6MYUYMPTGX/graph.json","fetch_events":"https://pith.science/api/pith-number/IGDYUUQOBNVRQUZR6MYUYMPTGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGDYUUQOBNVRQUZR6MYUYMPTGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGDYUUQOBNVRQUZR6MYUYMPTGX/action/storage_attestation","attest_author":"https://pith.science/pith/IGDYUUQOBNVRQUZR6MYUYMPTGX/action/author_attestation","sign_citation":"https://pith.science/pith/IGDYUUQOBNVRQUZR6MYUYMPTGX/action/citation_signature","submit_replication":"https://pith.science/pith/IGDYUUQOBNVRQUZR6MYUYMPTGX/action/replication_record"}},"created_at":"2026-07-05T11:43:53.740345+00:00","updated_at":"2026-07-05T11:43:53.740345+00:00"}