{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LSLJRAOPCDKV2VFMTIQAVF5V3J","short_pith_number":"pith:LSLJRAOP","schema_version":"1.0","canonical_sha256":"5c969881cf10d55d54ac9a200a97b5da46f931b836d9159efb6a57db478d030c","source":{"kind":"arxiv","id":"1902.04686","version":2},"attestation_state":"computed","paper":{"title":"The Complexity of Making the Gradient Small in Stochastic Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ayush Sekhari, Blake Woodworth, Dylan J. Foster, Karthik Sridharan, Nathan Srebro, Ohad Shamir","submitted_at":"2019-02-13T00:29:23Z","abstract_excerpt":"We give nearly matching upper and lower bounds on the oracle complexity of finding $\\epsilon$-stationary points ($\\| \\nabla F(x) \\| \\leq\\epsilon$) in stochastic convex optimization. We jointly analyze the oracle complexity in both the local stochastic oracle model and the global oracle (or, statistical learning) model. This allows us to decompose the complexity of finding near-stationary points into optimization complexity and sample complexity, and reveals some surprising differences between the complexity of stochastic optimization versus learning. Notably, we show that in the global oracle/"},"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":"1902.04686","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-13T00:29:23Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"5e5b6f21b1b0d6a6ad46840a8e8b3343219e9a4c406e39ec87cf9f9215d92dee","abstract_canon_sha256":"7da12b722d31e5ada69b0fbbb25844300ea012310b57c6cf53ef418274632d77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:02.007925Z","signature_b64":"qxhzgO3AQJdOGFQZ18etZLD4dTJgGQ4A1ZNsBTt9xS2D6D+BxVN9bsOaj7NifCccKMaG0fPxZyK70th1oCeFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c969881cf10d55d54ac9a200a97b5da46f931b836d9159efb6a57db478d030c","last_reissued_at":"2026-05-17T23:54:02.007434Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:02.007434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Complexity of Making the Gradient Small in Stochastic Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ayush Sekhari, Blake Woodworth, Dylan J. Foster, Karthik Sridharan, Nathan Srebro, Ohad Shamir","submitted_at":"2019-02-13T00:29:23Z","abstract_excerpt":"We give nearly matching upper and lower bounds on the oracle complexity of finding $\\epsilon$-stationary points ($\\| \\nabla F(x) \\| \\leq\\epsilon$) in stochastic convex optimization. We jointly analyze the oracle complexity in both the local stochastic oracle model and the global oracle (or, statistical learning) model. This allows us to decompose the complexity of finding near-stationary points into optimization complexity and sample complexity, and reveals some surprising differences between the complexity of stochastic optimization versus learning. Notably, we show that in the global oracle/"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04686","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":"1902.04686","created_at":"2026-05-17T23:54:02.007505+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.04686v2","created_at":"2026-05-17T23:54:02.007505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04686","created_at":"2026-05-17T23:54:02.007505+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSLJRAOPCDKV","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSLJRAOPCDKV2VFM","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSLJRAOP","created_at":"2026-05-18T12:33:21.387695+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/LSLJRAOPCDKV2VFMTIQAVF5V3J","json":"https://pith.science/pith/LSLJRAOPCDKV2VFMTIQAVF5V3J.json","graph_json":"https://pith.science/api/pith-number/LSLJRAOPCDKV2VFMTIQAVF5V3J/graph.json","events_json":"https://pith.science/api/pith-number/LSLJRAOPCDKV2VFMTIQAVF5V3J/events.json","paper":"https://pith.science/paper/LSLJRAOP"},"agent_actions":{"view_html":"https://pith.science/pith/LSLJRAOPCDKV2VFMTIQAVF5V3J","download_json":"https://pith.science/pith/LSLJRAOPCDKV2VFMTIQAVF5V3J.json","view_paper":"https://pith.science/paper/LSLJRAOP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.04686&json=true","fetch_graph":"https://pith.science/api/pith-number/LSLJRAOPCDKV2VFMTIQAVF5V3J/graph.json","fetch_events":"https://pith.science/api/pith-number/LSLJRAOPCDKV2VFMTIQAVF5V3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSLJRAOPCDKV2VFMTIQAVF5V3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSLJRAOPCDKV2VFMTIQAVF5V3J/action/storage_attestation","attest_author":"https://pith.science/pith/LSLJRAOPCDKV2VFMTIQAVF5V3J/action/author_attestation","sign_citation":"https://pith.science/pith/LSLJRAOPCDKV2VFMTIQAVF5V3J/action/citation_signature","submit_replication":"https://pith.science/pith/LSLJRAOPCDKV2VFMTIQAVF5V3J/action/replication_record"}},"created_at":"2026-05-17T23:54:02.007505+00:00","updated_at":"2026-05-17T23:54:02.007505+00:00"}