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.
Differentially private empirical risk minimization with non-convex loss functions
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Differential privacy in policy optimization adds sample complexity costs that often appear as lower-order terms rather than dominating the bounds.
citing papers explorer
-
Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov-Arnold Networks
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.
-
On the Sample Complexity of Differentially Private Policy Optimization
Differential privacy in policy optimization adds sample complexity costs that often appear as lower-order terms rather than dominating the bounds.