{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WMNEPMVC4VKSL3J5VJ7Z4OEHQB","short_pith_number":"pith:WMNEPMVC","schema_version":"1.0","canonical_sha256":"b31a47b2a2e55525ed3daa7f9e3887806bc7ad91be6cda14327d0a0e556be6c2","source":{"kind":"arxiv","id":"2601.22409","version":3},"attestation_state":"computed","paper":{"title":"Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov-Arnold Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Gradient descent on two-layer Kolmogorov-Arnold networks reaches optimization and generalization rates of order 1/T and 1/n with polylogarithmic width, and differential privacy makes that width necessary.","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junyu Zhou, Marius Kloft, Philipp Liznerski, Puyu Wang","submitted_at":"2026-01-29T23:43:26Z","abstract_excerpt":"Kolmogorov--Arnold Networks (KANs) have recently emerged as a structured alternative to standard MLPs, yet a principled theory for their training dynamics, generalization, and privacy properties remains limited. In this paper, we analyze gradient descent (GD) for training two-layer KANs and derive general bounds that characterize their training dynamics, generalization, and utility under differential privacy (DP). As a concrete instantiation, we specialize our analysis to logistic loss under an NTK-separable assumption, where we show that polylogarithmic network width suffices for GD to achiev"},"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":false},"canonical_record":{"source":{"id":"2601.22409","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T23:43:26Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a67079889d6ae0d1988e286ae7cff6a247eba891ada557e62dfe9ea129636f3e","abstract_canon_sha256":"47141e9eda08d6d56882e919e1ff514db52efcd61ed096650281dff17c08c4ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:24.080672Z","signature_b64":"HTQolPpuwrKgiacTJe6BnOG20WiSmCexxrkpZ2AOSmaL65WL5zCoAXUvd1vce4UUL/KQ0vyJjdDTbvj7v+POAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b31a47b2a2e55525ed3daa7f9e3887806bc7ad91be6cda14327d0a0e556be6c2","last_reissued_at":"2026-05-18T03:09:24.079935Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:24.079935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov-Arnold Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Gradient descent on two-layer Kolmogorov-Arnold networks reaches optimization and generalization rates of order 1/T and 1/n with polylogarithmic width, and differential privacy makes that width necessary.","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junyu Zhou, Marius Kloft, Philipp Liznerski, Puyu Wang","submitted_at":"2026-01-29T23:43:26Z","abstract_excerpt":"Kolmogorov--Arnold Networks (KANs) have recently emerged as a structured alternative to standard MLPs, yet a principled theory for their training dynamics, generalization, and privacy properties remains limited. In this paper, we analyze gradient descent (GD) for training two-layer KANs and derive general bounds that characterize their training dynamics, generalization, and utility under differential privacy (DP). As a concrete instantiation, we specialize our analysis to logistic loss under an NTK-separable assumption, where we show that polylogarithmic network width suffices for GD to achiev"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we show that polylogarithmic network width suffices for GD to achieve an optimization rate of order 1/T and a generalization rate of order 1/n ... obtain a utility bound of order √d/(nε) ... polylogarithmic width is not only sufficient but also necessary under differential privacy","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"NTK-separable assumption for the data under logistic loss, used to specialize the general analysis to achieve the stated rates","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"For two-layer KANs trained with gradient descent under logistic loss and NTK-separable assumption, polylogarithmic width suffices for 1/T optimization and 1/n generalization rates, while differential privacy requires the same width and yields √d/(nε) utility.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Gradient descent on two-layer Kolmogorov-Arnold networks reaches optimization and generalization rates of order 1/T and 1/n with polylogarithmic width, and differential privacy makes that width necessary.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7f8359b03914bff14bedb5c96f4dab39d9d58bd27566ba238088a4b535697157"},"source":{"id":"2601.22409","kind":"arxiv","version":3},"verdict":{"id":"8b259ed7-9cb5-4b06-8cc9-6577d66dec18","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T09:31:00.048163Z","strongest_claim":"we show that polylogarithmic network width suffices for GD to achieve an optimization rate of order 1/T and a generalization rate of order 1/n ... obtain a utility bound of order √d/(nε) ... polylogarithmic width is not only sufficient but also necessary under differential privacy","one_line_summary":"For two-layer KANs trained with gradient descent under logistic loss and NTK-separable assumption, polylogarithmic width suffices for 1/T optimization and 1/n generalization rates, while differential privacy requires the same width and yields √d/(nε) utility.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"NTK-separable assumption for the data under logistic loss, used to specialize the general analysis to achieve the stated rates","pith_extraction_headline":"Gradient descent on two-layer Kolmogorov-Arnold networks reaches optimization and generalization rates of order 1/T and 1/n with polylogarithmic width, and differential privacy makes that width necessary."},"references":{"count":73,"sample":[{"doi":"","year":2016,"title":"Deep learning with differential privacy","work_id":"a7375ed4-55e8-4d83-a877-6694ddafac56","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"A convergence theory for deep learning via over- parameterization","work_id":"2a252a94-ee15-4740-ac95-48e4c0bfa182","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1957,"title":"On functions of three variables","work_id":"c0039bc8-c8ed-4375-a027-1d4f381c914c","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks","work_id":"2f8744c1-d98b-482b-acc4-22e10362f492","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Spectrally-normalized margin bounds for neural networks.Advances in Neural Information Processing Systems, 30, 2017","work_id":"a70878f5-c8e2-48e1-8326-8c6c656e02dc","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":73,"snapshot_sha256":"85e5528b79021cf016f7d7443caee837c854c9a952d8b73bea0c1924b7dc7c5e","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":"2601.22409","created_at":"2026-05-18T03:09:24.080055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.22409v3","created_at":"2026-05-18T03:09:24.080055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22409","created_at":"2026-05-18T03:09:24.080055+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMNEPMVC4VKS","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMNEPMVC4VKSL3J5","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMNEPMVC","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMNEPMVC4VKSL3J5VJ7Z4OEHQB","json":"https://pith.science/pith/WMNEPMVC4VKSL3J5VJ7Z4OEHQB.json","graph_json":"https://pith.science/api/pith-number/WMNEPMVC4VKSL3J5VJ7Z4OEHQB/graph.json","events_json":"https://pith.science/api/pith-number/WMNEPMVC4VKSL3J5VJ7Z4OEHQB/events.json","paper":"https://pith.science/paper/WMNEPMVC"},"agent_actions":{"view_html":"https://pith.science/pith/WMNEPMVC4VKSL3J5VJ7Z4OEHQB","download_json":"https://pith.science/pith/WMNEPMVC4VKSL3J5VJ7Z4OEHQB.json","view_paper":"https://pith.science/paper/WMNEPMVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.22409&json=true","fetch_graph":"https://pith.science/api/pith-number/WMNEPMVC4VKSL3J5VJ7Z4OEHQB/graph.json","fetch_events":"https://pith.science/api/pith-number/WMNEPMVC4VKSL3J5VJ7Z4OEHQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMNEPMVC4VKSL3J5VJ7Z4OEHQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMNEPMVC4VKSL3J5VJ7Z4OEHQB/action/storage_attestation","attest_author":"https://pith.science/pith/WMNEPMVC4VKSL3J5VJ7Z4OEHQB/action/author_attestation","sign_citation":"https://pith.science/pith/WMNEPMVC4VKSL3J5VJ7Z4OEHQB/action/citation_signature","submit_replication":"https://pith.science/pith/WMNEPMVC4VKSL3J5VJ7Z4OEHQB/action/replication_record"}},"created_at":"2026-05-18T03:09:24.080055+00:00","updated_at":"2026-05-18T03:09:24.080055+00:00"}