{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LSMPQUTBB4O77I7OPBZUQLEMTP","short_pith_number":"pith:LSMPQUTB","schema_version":"1.0","canonical_sha256":"5c98f852610f1dffa3ee7873482c8c9bf7f16bf0113a0c273a09ffd2c5215065","source":{"kind":"arxiv","id":"1910.09529","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Gradient Descent without Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","stat.ML"],"primary_cat":"math.OC","authors_text":"Konstantin Mishchenko, Yura Malitsky","submitted_at":"2019-10-21T17:49:29Z","abstract_excerpt":"We present a strikingly simple proof that two rules are sufficient to automate gradient descent: 1) don't increase the stepsize too fast and 2) don't overstep the local curvature. No need for functional values, no line search, no information about the function except for the gradients. By following these rules, you get a method adaptive to the local geometry, with convergence guarantees depending only on the smoothness in a neighborhood of a solution. Given that the problem is convex, our method converges even if the global smoothness constant is infinity. As an illustration, it can minimize a"},"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":"1910.09529","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-10-21T17:49:29Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA","stat.ML"],"title_canon_sha256":"a56ad6f0ffe3e2cf043c6d3d7a119f5d5d7f6106450d5b9e15f01efb3ad7d81f","abstract_canon_sha256":"54702e064a21ba5eb2b48804b4a358468f76eac276048a1b31b9ce58f6c8f0e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:19.655277Z","signature_b64":"aAO2Vimv17Rke29VBj34ZcdySqOd2BdOnWJS/mMFMXyt/bjLZRrqwTarKzZu+sdmePm2fGOmsTEskQaGAzZHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c98f852610f1dffa3ee7873482c8c9bf7f16bf0113a0c273a09ffd2c5215065","last_reissued_at":"2026-07-05T01:27:19.654726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:19.654726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Gradient Descent without Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","stat.ML"],"primary_cat":"math.OC","authors_text":"Konstantin Mishchenko, Yura Malitsky","submitted_at":"2019-10-21T17:49:29Z","abstract_excerpt":"We present a strikingly simple proof that two rules are sufficient to automate gradient descent: 1) don't increase the stepsize too fast and 2) don't overstep the local curvature. No need for functional values, no line search, no information about the function except for the gradients. By following these rules, you get a method adaptive to the local geometry, with convergence guarantees depending only on the smoothness in a neighborhood of a solution. Given that the problem is convex, our method converges even if the global smoothness constant is infinity. As an illustration, it can minimize a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.09529","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.09529/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1910.09529","created_at":"2026-07-05T01:27:19.654794+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.09529v2","created_at":"2026-07-05T01:27:19.654794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.09529","created_at":"2026-07-05T01:27:19.654794+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSMPQUTBB4O7","created_at":"2026-07-05T01:27:19.654794+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSMPQUTBB4O77I7O","created_at":"2026-07-05T01:27:19.654794+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSMPQUTB","created_at":"2026-07-05T01:27:19.654794+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.14970","citing_title":"Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11515","citing_title":"Exponential Adaptive Smoothing and Importance Sampling for Optimization of the Conditional Value-at-Risk","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02787","citing_title":"Adaptive Accelerated Mirror Descent in Primal and Dual Spaces","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30930","citing_title":"SGD at the Edge of Stability: Stochastic Stabilization with Large Learning Rates","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14291","citing_title":"Projected gradient methods for nonconvex and stochastic smooth optimization: new complexities and auto-conditioned stepsizes","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11043","citing_title":"A Proximal Stochastic Gradient Method with Adaptive Step Size and Variance Reduction for Convex Composite Optimization","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04988","citing_title":"Adaptive Memory Momentum via a Model-Based Framework for Deep Learning Optimization","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00711","citing_title":"A Line-search-free Method for Adaptive Decentralized Optimization","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LSMPQUTBB4O77I7OPBZUQLEMTP","json":"https://pith.science/pith/LSMPQUTBB4O77I7OPBZUQLEMTP.json","graph_json":"https://pith.science/api/pith-number/LSMPQUTBB4O77I7OPBZUQLEMTP/graph.json","events_json":"https://pith.science/api/pith-number/LSMPQUTBB4O77I7OPBZUQLEMTP/events.json","paper":"https://pith.science/paper/LSMPQUTB"},"agent_actions":{"view_html":"https://pith.science/pith/LSMPQUTBB4O77I7OPBZUQLEMTP","download_json":"https://pith.science/pith/LSMPQUTBB4O77I7OPBZUQLEMTP.json","view_paper":"https://pith.science/paper/LSMPQUTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.09529&json=true","fetch_graph":"https://pith.science/api/pith-number/LSMPQUTBB4O77I7OPBZUQLEMTP/graph.json","fetch_events":"https://pith.science/api/pith-number/LSMPQUTBB4O77I7OPBZUQLEMTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSMPQUTBB4O77I7OPBZUQLEMTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSMPQUTBB4O77I7OPBZUQLEMTP/action/storage_attestation","attest_author":"https://pith.science/pith/LSMPQUTBB4O77I7OPBZUQLEMTP/action/author_attestation","sign_citation":"https://pith.science/pith/LSMPQUTBB4O77I7OPBZUQLEMTP/action/citation_signature","submit_replication":"https://pith.science/pith/LSMPQUTBB4O77I7OPBZUQLEMTP/action/replication_record"}},"created_at":"2026-07-05T01:27:19.654794+00:00","updated_at":"2026-07-05T01:27:19.654794+00:00"}