{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WMNEPMVC4VKSL3J5VJ7Z4OEHQB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"47141e9eda08d6d56882e919e1ff514db52efcd61ed096650281dff17c08c4ce","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T23:43:26Z","title_canon_sha256":"a67079889d6ae0d1988e286ae7cff6a247eba891ada557e62dfe9ea129636f3e"},"schema_version":"1.0","source":{"id":"2601.22409","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.22409","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2601.22409v3","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22409","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"WMNEPMVC4VKS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"WMNEPMVC4VKSL3J5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"WMNEPMVC","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:b957ac02746be59779f0eef9d3b71e5c0ff6cb69cd56a58dd0da4c3f41b7b43c","target":"graph","created_at":"2026-05-18T03:09:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"NTK-separable assumption for the data under logistic loss, used to specialize the general analysis to achieve the stated rates"},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"7f8359b03914bff14bedb5c96f4dab39d9d58bd27566ba238088a4b535697157"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Junyu Zhou, Marius Kloft, Philipp Liznerski, Puyu Wang","cross_cats":["cs.AI","stat.ML"],"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.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T23:43:26Z","title":"Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov-Arnold Networks"},"references":{"count":73,"internal_anchors":0,"resolved_work":73,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Deep learning with differential privacy","work_id":"a7375ed4-55e8-4d83-a877-6694ddafac56","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"A convergence theory for deep learning via over- parameterization","work_id":"2a252a94-ee15-4740-ac95-48e4c0bfa182","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"On functions of three variables","work_id":"c0039bc8-c8ed-4375-a027-1d4f381c914c","year":1957},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks","work_id":"2f8744c1-d98b-482b-acc4-22e10362f492","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Spectrally-normalized margin bounds for neural networks.Advances in Neural Information Processing Systems, 30, 2017","work_id":"a70878f5-c8e2-48e1-8326-8c6c656e02dc","year":2017}],"snapshot_sha256":"85e5528b79021cf016f7d7443caee837c854c9a952d8b73bea0c1924b7dc7c5e"},"source":{"id":"2601.22409","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T09:31:00.048163Z","id":"8b259ed7-9cb5-4b06-8cc9-6577d66dec18","model_set":{"reader":"grok-4.3"},"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","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.","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","weakest_assumption":"NTK-separable assumption for the data under logistic loss, used to specialize the general analysis to achieve the stated rates"}},"verdict_id":"8b259ed7-9cb5-4b06-8cc9-6577d66dec18"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d9cbbdb1745c781e21106a2e8774b401bf2ed06f89248241cbf505a5dc00aa7d","target":"record","created_at":"2026-05-18T03:09:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"47141e9eda08d6d56882e919e1ff514db52efcd61ed096650281dff17c08c4ce","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T23:43:26Z","title_canon_sha256":"a67079889d6ae0d1988e286ae7cff6a247eba891ada557e62dfe9ea129636f3e"},"schema_version":"1.0","source":{"id":"2601.22409","kind":"arxiv","version":3}},"canonical_sha256":"b31a47b2a2e55525ed3daa7f9e3887806bc7ad91be6cda14327d0a0e556be6c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b31a47b2a2e55525ed3daa7f9e3887806bc7ad91be6cda14327d0a0e556be6c2","first_computed_at":"2026-05-18T03:09:24.079935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:24.079935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HTQolPpuwrKgiacTJe6BnOG20WiSmCexxrkpZ2AOSmaL65WL5zCoAXUvd1vce4UUL/KQ0vyJjdDTbvj7v+POAg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:24.080672Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.22409","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9cbbdb1745c781e21106a2e8774b401bf2ed06f89248241cbf505a5dc00aa7d","sha256:b957ac02746be59779f0eef9d3b71e5c0ff6cb69cd56a58dd0da4c3f41b7b43c"],"state_sha256":"36ebac1230f417a34d635b844212124c4bf689d57895b71dde36175f0a61f1e0"}