{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:POMF6K33IYFDISZV2FCWMJP3VQ","short_pith_number":"pith:POMF6K33","schema_version":"1.0","canonical_sha256":"7b985f2b7b460a344b35d1456625fbac0f9e240db6a2efc084d54024d26db99c","source":{"kind":"arxiv","id":"1805.10367","version":2},"attestation_state":"computed","paper":{"title":"Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bhavya Kailkhura, Lisa Amini, Paishun Ting, Pin-Yu Chen, Shiyu Chang, Sijia Liu","submitted_at":"2018-05-25T21:18:19Z","abstract_excerpt":"As application demands for zeroth-order (gradient-free) optimization accelerate, the need for variance reduced and faster converging approaches is also intensifying. This paper addresses these challenges by presenting: a) a comprehensive theoretical analysis of variance reduced zeroth-order (ZO) optimization, b) a novel variance reduced ZO algorithm, called ZO-SVRG, and c) an experimental evaluation of our approach in the context of two compelling applications, black-box chemical material classification and generation of adversarial examples from black-box deep neural network models. Our theor"},"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":"1805.10367","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-25T21:18:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"694e42a7f1ac82f28d483e9bffd818604da8d0eedda6e0e523fe01dff12c2688","abstract_canon_sha256":"c7c45d2ddc434496522a4e686fa39c26957a78aea629966fcc51116bde02b5aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:57.391299Z","signature_b64":"lX25UWXLf2IIEnvd7csoawEx6g7q87C36s++YtgNtllCFkCoY9tpC/R/MMO6xXYI7i5p4GHx35TY0daJC5ayAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b985f2b7b460a344b35d1456625fbac0f9e240db6a2efc084d54024d26db99c","last_reissued_at":"2026-05-18T00:13:57.390685Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:57.390685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bhavya Kailkhura, Lisa Amini, Paishun Ting, Pin-Yu Chen, Shiyu Chang, Sijia Liu","submitted_at":"2018-05-25T21:18:19Z","abstract_excerpt":"As application demands for zeroth-order (gradient-free) optimization accelerate, the need for variance reduced and faster converging approaches is also intensifying. This paper addresses these challenges by presenting: a) a comprehensive theoretical analysis of variance reduced zeroth-order (ZO) optimization, b) a novel variance reduced ZO algorithm, called ZO-SVRG, and c) an experimental evaluation of our approach in the context of two compelling applications, black-box chemical material classification and generation of adversarial examples from black-box deep neural network models. Our theor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10367","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":"1805.10367","created_at":"2026-05-18T00:13:57.390773+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.10367v2","created_at":"2026-05-18T00:13:57.390773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10367","created_at":"2026-05-18T00:13:57.390773+00:00"},{"alias_kind":"pith_short_12","alias_value":"POMF6K33IYFD","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"POMF6K33IYFDISZV","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"POMF6K33","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16520","citing_title":"Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing","ref_index":141,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POMF6K33IYFDISZV2FCWMJP3VQ","json":"https://pith.science/pith/POMF6K33IYFDISZV2FCWMJP3VQ.json","graph_json":"https://pith.science/api/pith-number/POMF6K33IYFDISZV2FCWMJP3VQ/graph.json","events_json":"https://pith.science/api/pith-number/POMF6K33IYFDISZV2FCWMJP3VQ/events.json","paper":"https://pith.science/paper/POMF6K33"},"agent_actions":{"view_html":"https://pith.science/pith/POMF6K33IYFDISZV2FCWMJP3VQ","download_json":"https://pith.science/pith/POMF6K33IYFDISZV2FCWMJP3VQ.json","view_paper":"https://pith.science/paper/POMF6K33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.10367&json=true","fetch_graph":"https://pith.science/api/pith-number/POMF6K33IYFDISZV2FCWMJP3VQ/graph.json","fetch_events":"https://pith.science/api/pith-number/POMF6K33IYFDISZV2FCWMJP3VQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POMF6K33IYFDISZV2FCWMJP3VQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POMF6K33IYFDISZV2FCWMJP3VQ/action/storage_attestation","attest_author":"https://pith.science/pith/POMF6K33IYFDISZV2FCWMJP3VQ/action/author_attestation","sign_citation":"https://pith.science/pith/POMF6K33IYFDISZV2FCWMJP3VQ/action/citation_signature","submit_replication":"https://pith.science/pith/POMF6K33IYFDISZV2FCWMJP3VQ/action/replication_record"}},"created_at":"2026-05-18T00:13:57.390773+00:00","updated_at":"2026-05-18T00:13:57.390773+00:00"}