Paper proves orthogonal symmetry of the differential neural tangent kernel
Operators from the same group orbit share spectra, and shallow RePU networks get an eigenvalue decay rate.
Stories per day · 30 days
Relateddifferential-privacy1neural-tangent-kernel1orthogonal-group1physics-informed-neural-networks1privacy-certificates1renyi-divergence1
5 stories, newest first · one card per story
Stories tagged #kernel-methods
Kernel Stein discrepancies certify Rényi differential privacy
The paper gives exact identities for Gaussian and Laplace mechanisms and bounds for exponential mechanisms.
Subgroup Rank-1 Lattice for Practical High-dimensional Black-box Integral Approximation
A subgroup rank-1 lattice method speeds high-dimensional black-box integral estimates, including softmax attention, via FFT correlations.
A General Kernel Framework for Non-CND Distance Measures Using |D|-Dimensional Sparse Landmark Embeddings
Proposes the Sparse Landmark Embedding kernel, guaranteeing PSD kernels for arbitrary distances like geodesic and Wasserstein without CND requirements.
Fast Learning Rates for Physics-Informed Kernel Methods
Theoretical analysis proves finite-sample learning rates for physics-informed kernel estimators, showing differential observations can improve rates from n^-1/4 to n^-1/2.