{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WYOTTIM7ROJ4XIBGSHJUUJL54H","short_pith_number":"pith:WYOTTIM7","schema_version":"1.0","canonical_sha256":"b61d39a19f8b93cba02691d34a257de1c5155204de04de9c2df55619a9e876da","source":{"kind":"arxiv","id":"2605.09034","version":2},"attestation_state":"computed","paper":{"title":"Accelerating Zeroth-Order Spectral Optimization with Partial Orthogonalization from Power Iteration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Partial orthogonalization via power iteration accelerates zeroth-order fine-tuning of large language models.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiahe Chen, Ziye Ma","submitted_at":"2026-05-09T16:16:45Z","abstract_excerpt":"Zeroth-order (ZO) optimization has become increasingly popular and important in fine-tuning large language models (LLMs), especially on edge devices due to its ability to adjust the model to local data without the need for memory-intensive back-propagation. Recent works try to reduce ZO variance through low-dimensional subspace search, but subspace restriction alone leaves key optimization geometry under-exploited, motivating additional acceleration. In this work, we focus on the hidden layer training problem in which spectral optimizers like Muon outperform AdamW due to its ability to exploit"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.09034","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-09T16:16:45Z","cross_cats_sorted":[],"title_canon_sha256":"99cf8b2f472b177bbce07c93deb1fc36c779117d99a8bd71f72d650e982582fe","abstract_canon_sha256":"bb98591811764327e9dcc45e04ece45f1493c8f7f3df164546662746b696236a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:43.051519Z","signature_b64":"OTP+0y0m/M93qyTSH/F4hjfqBkpBl2LsjPRJV/AEvRwcMzVCG48GVy4k9evpsZt/eWrmv6Pip0UtcoJW1x7xAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b61d39a19f8b93cba02691d34a257de1c5155204de04de9c2df55619a9e876da","last_reissued_at":"2026-05-20T00:01:43.050728Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:43.050728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Zeroth-Order Spectral Optimization with Partial Orthogonalization from Power Iteration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Partial orthogonalization via power iteration accelerates zeroth-order fine-tuning of large language models.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiahe Chen, Ziye Ma","submitted_at":"2026-05-09T16:16:45Z","abstract_excerpt":"Zeroth-order (ZO) optimization has become increasingly popular and important in fine-tuning large language models (LLMs), especially on edge devices due to its ability to adjust the model to local data without the need for memory-intensive back-propagation. Recent works try to reduce ZO variance through low-dimensional subspace search, but subspace restriction alone leaves key optimization geometry under-exploited, motivating additional acceleration. In this work, we focus on the hidden layer training problem in which spectral optimizers like Muon outperform AdamW due to its ability to exploit"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on LLM fine-tuning show that our method can achieve from 1.5x to 4x the convergence speed of ZO-Muon, the current SOTA algorithm, across SuperGlue datasets in the OPT-13B model.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that projecting the search space onto a momentum-derived subspace sufficiently lowers gradient variance to stabilize the streaming power-iteration procedure and enable effective partial orthogonalization in the zeroth-order regime (abstract, paragraph on streaming variant).","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ZO-MOPI accelerates zeroth-order LLM fine-tuning by applying partial spectral orthogonalization from power iteration inside a momentum-projected subspace to reduce variance and exploit dominant directions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Partial orthogonalization via power iteration accelerates zeroth-order fine-tuning of large language models.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4d7a9efff25927d6fe9bd319bf8316ea0d31673a41574332e9d1b313f506d991"},"source":{"id":"2605.09034","kind":"arxiv","version":2},"verdict":{"id":"f74a27e0-851c-469c-8b5e-23f6c21784bd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T17:29:05.372590Z","strongest_claim":"Experiments on LLM fine-tuning show that our method can achieve from 1.5x to 4x the convergence speed of ZO-Muon, the current SOTA algorithm, across SuperGlue datasets in the OPT-13B model.","one_line_summary":"ZO-MOPI accelerates zeroth-order LLM fine-tuning by applying partial spectral orthogonalization from power iteration inside a momentum-projected subspace to reduce variance and exploit dominant directions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that projecting the search space onto a momentum-derived subspace sufficiently lowers gradient variance to stabilize the streaming power-iteration procedure and enable effective partial orthogonalization in the zeroth-order regime (abstract, paragraph on streaming variant).","pith_extraction_headline":"Partial orthogonalization via power iteration accelerates zeroth-order fine-tuning of large language models."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.09034/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T20:38:49.630487Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T13:31:19.289094Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T10:32:51.236600Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"914af79f9f85df6ed1c63de74cd5b79ec755b3e4e6dd922eeace2d9edc4b54bf"},"references":{"count":26,"sample":[{"doi":"","year":null,"title":"Dion: Distributed orthonormal- ized updates.arXiv preprint: 2504.05295","work_id":"4ecfbe15-0efd-41f4-a129-82f6a2164d2f","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Enhancing zeroth-order fine-tuning for language models with low-rank structures.arXiv preprint arXiv:2410.07698","work_id":"93562c56-6202-4ca4-a4de-cadf1aa59ee5","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Boolq: Exploring the surprising difficulty of natural yes/no questions","work_id":"873a4f9b-c4f6-4b39-8ae6-2abd7ce8e5ea","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Variance- reduced zeroth-order methods for fine-tuning language models.arXiv preprint arXiv:2404.08080","work_id":"781b7a33-777b-4e7b-8974-383845c8da8a","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"ARO : A New Lens On Matrix Optimization For Large Models","work_id":"0b1b41e4-a2fe-43e0-a97d-1b3ba9fbf25c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":26,"snapshot_sha256":"1ec1e7da4dddbe9d5ad8efa056ebdc2d257ab7925755acfb3b132a6f730c2107","internal_anchors":6},"formal_canon":{"evidence_count":2,"snapshot_sha256":"45419483cb771843c2b0efc9430898bd183041cf1e157286c56184090b577c40"},"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":"2605.09034","created_at":"2026-05-20T00:01:43.050868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.09034v2","created_at":"2026-05-20T00:01:43.050868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.09034","created_at":"2026-05-20T00:01:43.050868+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYOTTIM7ROJ4","created_at":"2026-05-20T00:01:43.050868+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYOTTIM7ROJ4XIBG","created_at":"2026-05-20T00:01:43.050868+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYOTTIM7","created_at":"2026-05-20T00:01:43.050868+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WYOTTIM7ROJ4XIBGSHJUUJL54H","json":"https://pith.science/pith/WYOTTIM7ROJ4XIBGSHJUUJL54H.json","graph_json":"https://pith.science/api/pith-number/WYOTTIM7ROJ4XIBGSHJUUJL54H/graph.json","events_json":"https://pith.science/api/pith-number/WYOTTIM7ROJ4XIBGSHJUUJL54H/events.json","paper":"https://pith.science/paper/WYOTTIM7"},"agent_actions":{"view_html":"https://pith.science/pith/WYOTTIM7ROJ4XIBGSHJUUJL54H","download_json":"https://pith.science/pith/WYOTTIM7ROJ4XIBGSHJUUJL54H.json","view_paper":"https://pith.science/paper/WYOTTIM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.09034&json=true","fetch_graph":"https://pith.science/api/pith-number/WYOTTIM7ROJ4XIBGSHJUUJL54H/graph.json","fetch_events":"https://pith.science/api/pith-number/WYOTTIM7ROJ4XIBGSHJUUJL54H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYOTTIM7ROJ4XIBGSHJUUJL54H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYOTTIM7ROJ4XIBGSHJUUJL54H/action/storage_attestation","attest_author":"https://pith.science/pith/WYOTTIM7ROJ4XIBGSHJUUJL54H/action/author_attestation","sign_citation":"https://pith.science/pith/WYOTTIM7ROJ4XIBGSHJUUJL54H/action/citation_signature","submit_replication":"https://pith.science/pith/WYOTTIM7ROJ4XIBGSHJUUJL54H/action/replication_record"}},"created_at":"2026-05-20T00:01:43.050868+00:00","updated_at":"2026-05-20T00:01:43.050868+00:00"}