LAPLEX: The FFT of Learnable Laplace Kernels 事件

LAPLEX: The FFT of Learnable Laplace Kernels arXiv:2605.24584v1 Announce Type: cross Abstract: Fast linear algebra in deep learning usually comes with a choice: fixed geometry and exact computation, as in the Fourier transform, or adaptive geometry paid for by dense parameters, random features, or low-rank surrogates. To move beyond this trade-off, we introduce LAPLEX, a class of exact, trainable (phased) Laplace-kernel operators. A LAPLEX layer is a typically full-rank dense matrix, implicit