5 problems

The normalized score functions are said to satisfy the non-uniform Lipschitz condition with constant $L$ if, for every $\tau\in(0,1)$, … Here $d$ is the dimension, $T$ is the relev…

Let $Z\sim\mathbb{N}(0,I_d)$ be Gaussian noise, let $t$ denote a diffusion time step, and let $\epsilon_\theta^{(t)}$ be the score network at time $t$. A score network is approxima…

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…

Let a data distribution have multimodal structure or be supported near a low-dimensional manifold, and consider score matching, including denoising score matching obtained by convo…

Lauritzen's conjecture. The graph $G$ is $n$-estimable if and only if