{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DQSCH6WD2WDDQ6QLFAXMI6AH7T","short_pith_number":"pith:DQSCH6WD","schema_version":"1.0","canonical_sha256":"1c2423fac3d586387a0b282ec47807fce81622487bef4aefd6c77c644611ee15","source":{"kind":"arxiv","id":"1712.03156","version":2},"attestation_state":"computed","paper":{"title":"Structure-Adaptive, Variance-Reduced, and Accelerated Stochastic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Francis Bach, Junqi Tang, Mike Davies, Mohammad Golbabaee","submitted_at":"2017-12-08T16:24:05Z","abstract_excerpt":"In this work we explore the fundamental structure-adaptiveness of state of the art randomized first order algorithms on regularized empirical risk minimization tasks, where the solution has intrinsic low-dimensional structure (such as sparsity and low-rank). Such structure is often enforced by non-smooth regularization or constraints. We start by establishing the fast linear convergence rate of the SAGA algorithm on non-strongly-convex objectives with convex constraints, via an argument of cone-restricted strong convexity. Then for the composite minimization task with a coordinate-wise separab"},"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":"1712.03156","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-12-08T16:24:05Z","cross_cats_sorted":[],"title_canon_sha256":"9bea0156d62978747c8e57a575be074cdda9717329641f032b27f267508753fa","abstract_canon_sha256":"31cd0973b1ef5429aa3686e914a79f60a490ad5938fa31f28061b59364a11abe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:09.797151Z","signature_b64":"vxZ++K7oZf8nAZLj9UWIgKp+2VYXiwns3KqWJt/Bet23GB5BQMniFJfeg/It2SiQFiChJNano4auB52apzwLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c2423fac3d586387a0b282ec47807fce81622487bef4aefd6c77c644611ee15","last_reissued_at":"2026-05-18T00:28:09.796526Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:09.796526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structure-Adaptive, Variance-Reduced, and Accelerated Stochastic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Francis Bach, Junqi Tang, Mike Davies, Mohammad Golbabaee","submitted_at":"2017-12-08T16:24:05Z","abstract_excerpt":"In this work we explore the fundamental structure-adaptiveness of state of the art randomized first order algorithms on regularized empirical risk minimization tasks, where the solution has intrinsic low-dimensional structure (such as sparsity and low-rank). Such structure is often enforced by non-smooth regularization or constraints. We start by establishing the fast linear convergence rate of the SAGA algorithm on non-strongly-convex objectives with convex constraints, via an argument of cone-restricted strong convexity. Then for the composite minimization task with a coordinate-wise separab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.03156","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":""},"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":"1712.03156","created_at":"2026-05-18T00:28:09.796597+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.03156v2","created_at":"2026-05-18T00:28:09.796597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.03156","created_at":"2026-05-18T00:28:09.796597+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQSCH6WD2WDD","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQSCH6WD2WDDQ6QL","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQSCH6WD","created_at":"2026-05-18T12:31:12.930513+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/DQSCH6WD2WDDQ6QLFAXMI6AH7T","json":"https://pith.science/pith/DQSCH6WD2WDDQ6QLFAXMI6AH7T.json","graph_json":"https://pith.science/api/pith-number/DQSCH6WD2WDDQ6QLFAXMI6AH7T/graph.json","events_json":"https://pith.science/api/pith-number/DQSCH6WD2WDDQ6QLFAXMI6AH7T/events.json","paper":"https://pith.science/paper/DQSCH6WD"},"agent_actions":{"view_html":"https://pith.science/pith/DQSCH6WD2WDDQ6QLFAXMI6AH7T","download_json":"https://pith.science/pith/DQSCH6WD2WDDQ6QLFAXMI6AH7T.json","view_paper":"https://pith.science/paper/DQSCH6WD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.03156&json=true","fetch_graph":"https://pith.science/api/pith-number/DQSCH6WD2WDDQ6QLFAXMI6AH7T/graph.json","fetch_events":"https://pith.science/api/pith-number/DQSCH6WD2WDDQ6QLFAXMI6AH7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQSCH6WD2WDDQ6QLFAXMI6AH7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQSCH6WD2WDDQ6QLFAXMI6AH7T/action/storage_attestation","attest_author":"https://pith.science/pith/DQSCH6WD2WDDQ6QLFAXMI6AH7T/action/author_attestation","sign_citation":"https://pith.science/pith/DQSCH6WD2WDDQ6QLFAXMI6AH7T/action/citation_signature","submit_replication":"https://pith.science/pith/DQSCH6WD2WDDQ6QLFAXMI6AH7T/action/replication_record"}},"created_at":"2026-05-18T00:28:09.796597+00:00","updated_at":"2026-05-18T00:28:09.796597+00:00"}