{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BT3Q3BY7WE7PTIE7GZGFD43BNV","short_pith_number":"pith:BT3Q3BY7","schema_version":"1.0","canonical_sha256":"0cf70d871fb13ef9a09f364c51f3616d417783ec52ffd728585fca927f2afe67","source":{"kind":"arxiv","id":"2507.09823","version":2},"attestation_state":"computed","paper":{"title":"Nesterov Finds GRAAL: Optimal and Adaptive Gradient Method for Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Dmitry Kovalev, Ekaterina Borodich","submitted_at":"2025-07-13T23:07:45Z","abstract_excerpt":"In this paper, we focus on the problem of minimizing a continuously differentiable convex objective function, $\\min_x f(x)$. Recently, Malitsky (2020); Alacaoglu et al.(2023) developed an adaptive first-order method, GRAAL. This algorithm computes stepsizes by estimating the local curvature of the objective function without any line search procedures or hyperparameter tuning, and attains the standard iteration complexity $\\mathcal{O}(L\\lVert x_0-x^*\\rVert^2/\\epsilon)$ of fixed-stepsize gradient descent for $L$-smooth functions. However, a natural question arises: is it possible to accelerate t"},"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":"2507.09823","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-07-13T23:07:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"aeb54191fda8f298f975b809b238db3b301837afa3cc0e8acdacfbe46e419984","abstract_canon_sha256":"aa88f9c3d4e3e32c00f56dafa043880471bc1824bdf6d8fae783b0969fa0f35c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:45.936255Z","signature_b64":"4uM7wa/DDyzlbUtRWDuVKQRchytM1EGKwCaHXHZj92PHQWNYAdhWK2g63upiczh3wOYK62uUpAHtGOCuo22hCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cf70d871fb13ef9a09f364c51f3616d417783ec52ffd728585fca927f2afe67","last_reissued_at":"2026-07-05T12:01:45.935727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:45.935727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nesterov Finds GRAAL: Optimal and Adaptive Gradient Method for Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Dmitry Kovalev, Ekaterina Borodich","submitted_at":"2025-07-13T23:07:45Z","abstract_excerpt":"In this paper, we focus on the problem of minimizing a continuously differentiable convex objective function, $\\min_x f(x)$. Recently, Malitsky (2020); Alacaoglu et al.(2023) developed an adaptive first-order method, GRAAL. This algorithm computes stepsizes by estimating the local curvature of the objective function without any line search procedures or hyperparameter tuning, and attains the standard iteration complexity $\\mathcal{O}(L\\lVert x_0-x^*\\rVert^2/\\epsilon)$ of fixed-stepsize gradient descent for $L$-smooth functions. However, a natural question arises: is it possible to accelerate t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09823","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/2507.09823/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":"2507.09823","created_at":"2026-07-05T12:01:45.935811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09823v2","created_at":"2026-07-05T12:01:45.935811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09823","created_at":"2026-07-05T12:01:45.935811+00:00"},{"alias_kind":"pith_short_12","alias_value":"BT3Q3BY7WE7P","created_at":"2026-07-05T12:01:45.935811+00:00"},{"alias_kind":"pith_short_16","alias_value":"BT3Q3BY7WE7PTIE7","created_at":"2026-07-05T12:01:45.935811+00:00"},{"alias_kind":"pith_short_8","alias_value":"BT3Q3BY7","created_at":"2026-07-05T12:01:45.935811+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.23492","citing_title":"Universal and Parameter-free Gradient Sliding for Composite Optimization","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BT3Q3BY7WE7PTIE7GZGFD43BNV","json":"https://pith.science/pith/BT3Q3BY7WE7PTIE7GZGFD43BNV.json","graph_json":"https://pith.science/api/pith-number/BT3Q3BY7WE7PTIE7GZGFD43BNV/graph.json","events_json":"https://pith.science/api/pith-number/BT3Q3BY7WE7PTIE7GZGFD43BNV/events.json","paper":"https://pith.science/paper/BT3Q3BY7"},"agent_actions":{"view_html":"https://pith.science/pith/BT3Q3BY7WE7PTIE7GZGFD43BNV","download_json":"https://pith.science/pith/BT3Q3BY7WE7PTIE7GZGFD43BNV.json","view_paper":"https://pith.science/paper/BT3Q3BY7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09823&json=true","fetch_graph":"https://pith.science/api/pith-number/BT3Q3BY7WE7PTIE7GZGFD43BNV/graph.json","fetch_events":"https://pith.science/api/pith-number/BT3Q3BY7WE7PTIE7GZGFD43BNV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BT3Q3BY7WE7PTIE7GZGFD43BNV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BT3Q3BY7WE7PTIE7GZGFD43BNV/action/storage_attestation","attest_author":"https://pith.science/pith/BT3Q3BY7WE7PTIE7GZGFD43BNV/action/author_attestation","sign_citation":"https://pith.science/pith/BT3Q3BY7WE7PTIE7GZGFD43BNV/action/citation_signature","submit_replication":"https://pith.science/pith/BT3Q3BY7WE7PTIE7GZGFD43BNV/action/replication_record"}},"created_at":"2026-07-05T12:01:45.935811+00:00","updated_at":"2026-07-05T12:01:45.935811+00:00"}