6 problems

Let $\Theta$ be the neural tangent kernel of a diffusion model and let $k_H$ denote the Hellinger kernel of its data distribution. A Hellinger kernel is understood here as the uniq…

Let the score be approximated by a neural network, for example in the neural tangent kernel regime, and let the neural tangent kernel (NTK) have an equivalent kernel. Kernel-convol…

Random evolving neural tangent kernel conjecture. In the MoGP case, when the Lévy measure is non-trivial, the infinite-width limit should yield a random kernel, and this kernel sho…

For the neural-network model $\mathcal{F}_{\tanh}$, let $L$ denote the depth and $D$ the dimension, and consider the limits in which both parameters grow unboundedly for the smooth…

Consider a multi-layer neural network in the linear-width asymptotic regime, and let the activation function be $sigma$. Assume that … Let the conjugate-kernel spectrum have a limi…

Let $d$ denote network depth and $n$ denote network width, and consider fully connected ReLU networks in the overparameterized limit where both $d$ and $n$ are large. Weak feature…