{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NGSYS47DXMGQITW2PM4RBBYWHB","short_pith_number":"pith:NGSYS47D","schema_version":"1.0","canonical_sha256":"69a58973e3bb0d044eda7b3910871638492996b1854b17d386c9a3d9dd8b4b20","source":{"kind":"arxiv","id":"2502.02002","version":2},"attestation_state":"computed","paper":{"title":"The Ball-Proximal (=\"Broximal\") Point Method: a New Algorithm, Convergence Theory, and Applications","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Aadi Rane, Hanmin Li, Kaja Gruntkowska, Peter Richt\\'arik","submitted_at":"2025-02-04T04:30:03Z","abstract_excerpt":"Non-smooth and non-convex global optimization poses significant challenges across various applications, where standard gradient-based methods often struggle. We propose the Ball-Proximal Point Method, Broximal Point Method, or Ball Point Method (BPM) for short - a novel algorithmic framework inspired by the classical Proximal Point Method (PPM) (Rockafellar, 1976), which, as we show, sheds new light on several foundational optimization paradigms and phenomena, including non-convex and non-smooth optimization, acceleration, smoothing, adaptive stepsize selection, and trust-region methods. At th"},"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":"2502.02002","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"math.OC","submitted_at":"2025-02-04T04:30:03Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"9eb6c3af676eef50c76bbf4d35e0a2046c707ca3b1c90f56d0c99d0b34d253eb","abstract_canon_sha256":"62d0f7d0fffd9c7a256f0115c64b1ee904bb6ebd813bdfbc97b7f330f434105d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:31.233261Z","signature_b64":"JCT6DvbIK/llVZKTi11T1xxujH1UMV2BPjl/beYsNcUPSxZivYRevrM966reD4NFN0GFpiYGKPH+Vlpp2dmkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69a58973e3bb0d044eda7b3910871638492996b1854b17d386c9a3d9dd8b4b20","last_reissued_at":"2026-07-05T11:45:31.232766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:31.232766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Ball-Proximal (=\"Broximal\") Point Method: a New Algorithm, Convergence Theory, and Applications","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Aadi Rane, Hanmin Li, Kaja Gruntkowska, Peter Richt\\'arik","submitted_at":"2025-02-04T04:30:03Z","abstract_excerpt":"Non-smooth and non-convex global optimization poses significant challenges across various applications, where standard gradient-based methods often struggle. We propose the Ball-Proximal Point Method, Broximal Point Method, or Ball Point Method (BPM) for short - a novel algorithmic framework inspired by the classical Proximal Point Method (PPM) (Rockafellar, 1976), which, as we show, sheds new light on several foundational optimization paradigms and phenomena, including non-convex and non-smooth optimization, acceleration, smoothing, adaptive stepsize selection, and trust-region methods. At th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02002","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/2502.02002/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":"2502.02002","created_at":"2026-07-05T11:45:31.232829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02002v2","created_at":"2026-07-05T11:45:31.232829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02002","created_at":"2026-07-05T11:45:31.232829+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGSYS47DXMGQ","created_at":"2026-07-05T11:45:31.232829+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGSYS47DXMGQITW2","created_at":"2026-07-05T11:45:31.232829+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGSYS47D","created_at":"2026-07-05T11:45:31.232829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.12314","citing_title":"A smoothing moving balls approximation method for a class of conic-constrained difference-of-convex optimization problems","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13434","citing_title":"Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02943","citing_title":"Stabilized Proximal Point Method via Trust Region Control","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08850","citing_title":"Local LMO: Constrained Gradient Optimization via a Local Linear Minimization Oracle","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03815","citing_title":"Ball-proximal point method on a Hadamard Manifolds","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NGSYS47DXMGQITW2PM4RBBYWHB","json":"https://pith.science/pith/NGSYS47DXMGQITW2PM4RBBYWHB.json","graph_json":"https://pith.science/api/pith-number/NGSYS47DXMGQITW2PM4RBBYWHB/graph.json","events_json":"https://pith.science/api/pith-number/NGSYS47DXMGQITW2PM4RBBYWHB/events.json","paper":"https://pith.science/paper/NGSYS47D"},"agent_actions":{"view_html":"https://pith.science/pith/NGSYS47DXMGQITW2PM4RBBYWHB","download_json":"https://pith.science/pith/NGSYS47DXMGQITW2PM4RBBYWHB.json","view_paper":"https://pith.science/paper/NGSYS47D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02002&json=true","fetch_graph":"https://pith.science/api/pith-number/NGSYS47DXMGQITW2PM4RBBYWHB/graph.json","fetch_events":"https://pith.science/api/pith-number/NGSYS47DXMGQITW2PM4RBBYWHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGSYS47DXMGQITW2PM4RBBYWHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGSYS47DXMGQITW2PM4RBBYWHB/action/storage_attestation","attest_author":"https://pith.science/pith/NGSYS47DXMGQITW2PM4RBBYWHB/action/author_attestation","sign_citation":"https://pith.science/pith/NGSYS47DXMGQITW2PM4RBBYWHB/action/citation_signature","submit_replication":"https://pith.science/pith/NGSYS47DXMGQITW2PM4RBBYWHB/action/replication_record"}},"created_at":"2026-07-05T11:45:31.232829+00:00","updated_at":"2026-07-05T11:45:31.232829+00:00"}