{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:H7XULGZZLMCZOJRUPBCH7SCBCY","short_pith_number":"pith:H7XULGZZ","schema_version":"1.0","canonical_sha256":"3fef459b395b0597263478447fc84116239c772e87fd721d2fbb7c10f57296ca","source":{"kind":"arxiv","id":"1506.02227","version":1},"attestation_state":"computed","paper":{"title":"Primal Method for ERM with Flexible Mini-batching Schemes and Non-convex Losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Dominik Csiba, Peter Richt\\'arik","submitted_at":"2015-06-07T06:45:55Z","abstract_excerpt":"In this work we develop a new algorithm for regularized empirical risk minimization. Our method extends recent techniques of Shalev-Shwartz [02/2015], which enable a dual-free analysis of SDCA, to arbitrary mini-batching schemes. Moreover, our method is able to better utilize the information in the data defining the ERM problem. For convex loss functions, our complexity results match those of QUARTZ, which is a primal-dual method also allowing for arbitrary mini-batching schemes. The advantage of a dual-free analysis comes from the fact that it guarantees convergence even for non-convex loss f"},"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":"1506.02227","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2015-06-07T06:45:55Z","cross_cats_sorted":["cs.DS","cs.LG","stat.ML"],"title_canon_sha256":"63d379002c66b57b98ac559d131683cbcb24daec2129c6a5d4f30c6ab84a732a","abstract_canon_sha256":"bb1931a4fb16389eb9935079c52cb50836783f28b8a5a97685b499aa897eb976"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:55:51.791642Z","signature_b64":"LA2GkGWIaJNQYqbCl3qzt5YVVcubv+FexwgMUnXWomWJFAbRUj05oF6Clrn3/kYpEMh9DnMjZnL36chPz2+iAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fef459b395b0597263478447fc84116239c772e87fd721d2fbb7c10f57296ca","last_reissued_at":"2026-05-18T01:55:51.790969Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:55:51.790969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Primal Method for ERM with Flexible Mini-batching Schemes and Non-convex Losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Dominik Csiba, Peter Richt\\'arik","submitted_at":"2015-06-07T06:45:55Z","abstract_excerpt":"In this work we develop a new algorithm for regularized empirical risk minimization. Our method extends recent techniques of Shalev-Shwartz [02/2015], which enable a dual-free analysis of SDCA, to arbitrary mini-batching schemes. Moreover, our method is able to better utilize the information in the data defining the ERM problem. For convex loss functions, our complexity results match those of QUARTZ, which is a primal-dual method also allowing for arbitrary mini-batching schemes. The advantage of a dual-free analysis comes from the fact that it guarantees convergence even for non-convex loss f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02227","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":""},"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":"1506.02227","created_at":"2026-05-18T01:55:51.791081+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.02227v1","created_at":"2026-05-18T01:55:51.791081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02227","created_at":"2026-05-18T01:55:51.791081+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7XULGZZLMCZ","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7XULGZZLMCZOJRU","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7XULGZZ","created_at":"2026-05-18T12:29:22.688609+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/H7XULGZZLMCZOJRUPBCH7SCBCY","json":"https://pith.science/pith/H7XULGZZLMCZOJRUPBCH7SCBCY.json","graph_json":"https://pith.science/api/pith-number/H7XULGZZLMCZOJRUPBCH7SCBCY/graph.json","events_json":"https://pith.science/api/pith-number/H7XULGZZLMCZOJRUPBCH7SCBCY/events.json","paper":"https://pith.science/paper/H7XULGZZ"},"agent_actions":{"view_html":"https://pith.science/pith/H7XULGZZLMCZOJRUPBCH7SCBCY","download_json":"https://pith.science/pith/H7XULGZZLMCZOJRUPBCH7SCBCY.json","view_paper":"https://pith.science/paper/H7XULGZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.02227&json=true","fetch_graph":"https://pith.science/api/pith-number/H7XULGZZLMCZOJRUPBCH7SCBCY/graph.json","fetch_events":"https://pith.science/api/pith-number/H7XULGZZLMCZOJRUPBCH7SCBCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7XULGZZLMCZOJRUPBCH7SCBCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7XULGZZLMCZOJRUPBCH7SCBCY/action/storage_attestation","attest_author":"https://pith.science/pith/H7XULGZZLMCZOJRUPBCH7SCBCY/action/author_attestation","sign_citation":"https://pith.science/pith/H7XULGZZLMCZOJRUPBCH7SCBCY/action/citation_signature","submit_replication":"https://pith.science/pith/H7XULGZZLMCZOJRUPBCH7SCBCY/action/replication_record"}},"created_at":"2026-05-18T01:55:51.791081+00:00","updated_at":"2026-05-18T01:55:51.791081+00:00"}