{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:DSISX2HW5JFINBMM2OUOYBXS2X","short_pith_number":"pith:DSISX2HW","schema_version":"1.0","canonical_sha256":"1c912be8f6ea4a86858cd3a8ec06f2d5fd1b72276234f817ef79433fc8fde42a","source":{"kind":"arxiv","id":"1502.02846","version":4},"attestation_state":"computed","paper":{"title":"Probabilistic Line Searches for Stochastic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Maren Mahsereci, Philipp Hennig","submitted_at":"2015-02-10T10:36:25Z","abstract_excerpt":"In deterministic optimization, line searches are a standard tool ensuring stability and efficiency. Where only stochastic gradients are available, no direct equivalent has so far been formulated, because uncertain gradients do not allow for a strict sequence of decisions collapsing the search space. We construct a probabilistic line search by combining the structure of existing deterministic methods with notions from Bayesian optimization. Our method retains a Gaussian process surrogate of the univariate optimization objective, and uses a probabilistic belief over the Wolfe conditions to monit"},"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":"1502.02846","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-10T10:36:25Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"71ee476fcb46db4b1735852993a8562e8c828dc210c6d41d2351c13c04cc9f3d","abstract_canon_sha256":"9914889930204f0873c91750fcd5856bc4d1e38607d1d43f596bceddc5700e21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:22:48.616153Z","signature_b64":"2c9lih123w4qdzZ/k6nGfqJgl1fWA0Ov/CPX6LPyIr4zwwAl2NomWY8RFcmmKOtf0qTDu5lYs30+KFBv0Z7MBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c912be8f6ea4a86858cd3a8ec06f2d5fd1b72276234f817ef79433fc8fde42a","last_reissued_at":"2026-05-18T01:22:48.615661Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:22:48.615661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic Line Searches for Stochastic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Maren Mahsereci, Philipp Hennig","submitted_at":"2015-02-10T10:36:25Z","abstract_excerpt":"In deterministic optimization, line searches are a standard tool ensuring stability and efficiency. Where only stochastic gradients are available, no direct equivalent has so far been formulated, because uncertain gradients do not allow for a strict sequence of decisions collapsing the search space. We construct a probabilistic line search by combining the structure of existing deterministic methods with notions from Bayesian optimization. Our method retains a Gaussian process surrogate of the univariate optimization objective, and uses a probabilistic belief over the Wolfe conditions to monit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.02846","kind":"arxiv","version":4},"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":"1502.02846","created_at":"2026-05-18T01:22:48.615740+00:00"},{"alias_kind":"arxiv_version","alias_value":"1502.02846v4","created_at":"2026-05-18T01:22:48.615740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.02846","created_at":"2026-05-18T01:22:48.615740+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSISX2HW5JFI","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSISX2HW5JFINBMM","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSISX2HW","created_at":"2026-05-18T12:29:17.054201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2212.08989","citing_title":"Deep learning applied to computational mechanics: A comprehensive review, state of the art, and the classics","ref_index":149,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DSISX2HW5JFINBMM2OUOYBXS2X","json":"https://pith.science/pith/DSISX2HW5JFINBMM2OUOYBXS2X.json","graph_json":"https://pith.science/api/pith-number/DSISX2HW5JFINBMM2OUOYBXS2X/graph.json","events_json":"https://pith.science/api/pith-number/DSISX2HW5JFINBMM2OUOYBXS2X/events.json","paper":"https://pith.science/paper/DSISX2HW"},"agent_actions":{"view_html":"https://pith.science/pith/DSISX2HW5JFINBMM2OUOYBXS2X","download_json":"https://pith.science/pith/DSISX2HW5JFINBMM2OUOYBXS2X.json","view_paper":"https://pith.science/paper/DSISX2HW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1502.02846&json=true","fetch_graph":"https://pith.science/api/pith-number/DSISX2HW5JFINBMM2OUOYBXS2X/graph.json","fetch_events":"https://pith.science/api/pith-number/DSISX2HW5JFINBMM2OUOYBXS2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSISX2HW5JFINBMM2OUOYBXS2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSISX2HW5JFINBMM2OUOYBXS2X/action/storage_attestation","attest_author":"https://pith.science/pith/DSISX2HW5JFINBMM2OUOYBXS2X/action/author_attestation","sign_citation":"https://pith.science/pith/DSISX2HW5JFINBMM2OUOYBXS2X/action/citation_signature","submit_replication":"https://pith.science/pith/DSISX2HW5JFINBMM2OUOYBXS2X/action/replication_record"}},"created_at":"2026-05-18T01:22:48.615740+00:00","updated_at":"2026-05-18T01:22:48.615740+00:00"}