collaborators

7 papers

cs.LG2026

Bernstein-Schur Kernels: Random Features by Sketched Modulation and Radial Randomization

Taha Bouhsine

Bernstein--Schur kernels are products of a finite-feature kernel and a completely monotone shift-invariant kernel: nonstationary kernels falling between the shift-invariant and dot…

cs.LG2026

In Defense of Cosine Similarity: Normalization Eliminates the Gauge Freedom

Taha Bouhsine

Steck, Ekanadham, and Kallus [arXiv:2403.05440] demonstrate that cosine similarity of learned embeddings from matrix factorization models can be rendered arbitrary by a diagonal ``…

cs.LG2026

A Universal Reproducing Kernel Hilbert Space from Polynomial Alignment and IMQ Distance

Taha Bouhsine

We introduce the Yat kernel $$k_{b,\varepsilon}(\mathbf{w},\mathbf{x})=\frac{(\mathbf{w}^\top\mathbf{x}+b)^2}{\|\mathbf{x}-\mathbf{w}\|^2+\varepsilon},\qquad b\ge 0,\ \varepsilon>0…

cs.LG2026

No More DeLuLu: Physics-Inspired Kernel Networks for Geometrically-Grounded Neural Computation

Taha Bouhsine

We introduce the yat-product, a kernel operator combining quadratic alignment with inverse-square proximity. We prove it is a Mercer kernel, analytic, Lipschitz on bounded domains,…

cs.LG2026

SLAY: Geometry-Aware Spherical Linearized Attention with Yat-Kernel

Jose Miguel Luna, Taha Bouhsine, Krzysztof Choromanski

We propose a new class of linear-time attention mechanisms based on a relaxed and computationally efficient formulation of the recently introduced E-Product, often referred to as t…

cs.LG2024

Deep Learning 2.0: Artificial Neurons That Matter -- Reject Correlation, Embrace Orthogonality

Taha Bouhsine

We introduce a yat-product-powered neural network, the Neural Matter Network (NMN), a breakthrough in deep learning that achieves non-linear pattern recognition without activation…