{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:E4JF2PAAPNHYAY2QFHNXJUAZGE","short_pith_number":"pith:E4JF2PAA","schema_version":"1.0","canonical_sha256":"27125d3c007b4f80635029db74d019311f863a5c83c9eadaff6fa1d1cf24215a","source":{"kind":"arxiv","id":"1905.00313","version":2},"attestation_state":"computed","paper":{"title":"Revisiting the Polyak step size","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Elad Hazan, Sham Kakade","submitted_at":"2019-05-01T13:47:40Z","abstract_excerpt":"This paper revisits the Polyak step size schedule for convex optimization problems, proving that a simple variant of it simultaneously attains near optimal convergence rates for the gradient descent algorithm, for all ranges of strong convexity, smoothness, and Lipschitz parameters, without a-priory knowledge of these parameters."},"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":"1905.00313","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-05-01T13:47:40Z","cross_cats_sorted":[],"title_canon_sha256":"c62ffa817fdd22e75bf1c3eb9c4a5a608bf1fcfc66c7eef6eb8fde649220e607","abstract_canon_sha256":"fb228248f654ab76b3fac08d119fe28df476eedfae551ba851722e88ee346f81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:08.477053Z","signature_b64":"mZB+DzFGx2KAgDJfTquTHc1imqDj6+hD0VG5ixxupNAXomXR1I3LrUXxHNtjXEKxGryI8qr0HJ5fGevA0RiICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27125d3c007b4f80635029db74d019311f863a5c83c9eadaff6fa1d1cf24215a","last_reissued_at":"2026-07-05T04:45:08.476261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:08.476261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting the Polyak step size","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Elad Hazan, Sham Kakade","submitted_at":"2019-05-01T13:47:40Z","abstract_excerpt":"This paper revisits the Polyak step size schedule for convex optimization problems, proving that a simple variant of it simultaneously attains near optimal convergence rates for the gradient descent algorithm, for all ranges of strong convexity, smoothness, and Lipschitz parameters, without a-priory knowledge of these parameters."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.00313","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/1905.00313/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":"1905.00313","created_at":"2026-07-05T04:45:08.476396+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.00313v2","created_at":"2026-07-05T04:45:08.476396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.00313","created_at":"2026-07-05T04:45:08.476396+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4JF2PAAPNHY","created_at":"2026-07-05T04:45:08.476396+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4JF2PAAPNHYAY2Q","created_at":"2026-07-05T04:45:08.476396+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4JF2PAA","created_at":"2026-07-05T04:45:08.476396+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21354","citing_title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","ref_index":133,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07841","citing_title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03953","citing_title":"Introduction to stochastic gradient methods","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01827","citing_title":"Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Scheduler","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06319","citing_title":"Uniformly Optimal and Parameter-free First-order Methods for Convex and Function-constrained Optimization","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05482","citing_title":"Stein Diffusion Guidance: Training-Free Posterior Correction for Sampling Beyond High-Density Regions","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2511.07767","citing_title":"Taking the Road Less Scheduled with Adaptive Polyak Steps","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10183","citing_title":"Fix the Loss, Not the Radius: Rethinking the Adversarial Perturbation of Sharpness-Aware Minimization","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13393","citing_title":"A short proof of near-linear convergence of adaptive gradient descent under fourth-order growth and convexity","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E4JF2PAAPNHYAY2QFHNXJUAZGE","json":"https://pith.science/pith/E4JF2PAAPNHYAY2QFHNXJUAZGE.json","graph_json":"https://pith.science/api/pith-number/E4JF2PAAPNHYAY2QFHNXJUAZGE/graph.json","events_json":"https://pith.science/api/pith-number/E4JF2PAAPNHYAY2QFHNXJUAZGE/events.json","paper":"https://pith.science/paper/E4JF2PAA"},"agent_actions":{"view_html":"https://pith.science/pith/E4JF2PAAPNHYAY2QFHNXJUAZGE","download_json":"https://pith.science/pith/E4JF2PAAPNHYAY2QFHNXJUAZGE.json","view_paper":"https://pith.science/paper/E4JF2PAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.00313&json=true","fetch_graph":"https://pith.science/api/pith-number/E4JF2PAAPNHYAY2QFHNXJUAZGE/graph.json","fetch_events":"https://pith.science/api/pith-number/E4JF2PAAPNHYAY2QFHNXJUAZGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4JF2PAAPNHYAY2QFHNXJUAZGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4JF2PAAPNHYAY2QFHNXJUAZGE/action/storage_attestation","attest_author":"https://pith.science/pith/E4JF2PAAPNHYAY2QFHNXJUAZGE/action/author_attestation","sign_citation":"https://pith.science/pith/E4JF2PAAPNHYAY2QFHNXJUAZGE/action/citation_signature","submit_replication":"https://pith.science/pith/E4JF2PAAPNHYAY2QFHNXJUAZGE/action/replication_record"}},"created_at":"2026-07-05T04:45:08.476396+00:00","updated_at":"2026-07-05T04:45:08.476396+00:00"}