关于具有对称散度的图拉普拉斯算子的收敛性
On the convergence of graph Laplacians with a symmetric divergence
AI总结:
研究在特定黎曼子流形上,基于满足条件的对称散度$D$构造图拉普拉斯算子,证明其逐点收敛性,并给出$D$由Sinkhorn散度给出的例子。
摘要:
在分析位于光滑、紧致、连通的黎曼子流形$(\mathcal{M}, g)$上的数据的流形学习算法时,测地距离$d_g$的一个关键估计是存在$K > 0$,使得对于所有$p, q \in \mathcal{M}$,有$0 \leq d_g(p, q)^2 - \|p - q\|^2 \leq K d_g(p, q)^4$。更一般地,当$\mathcal{M}$配备满足非退化条件的光滑对称散度$D$且$g_p := \frac{1}{2}\mathrm{Hess}_p(D(p, \cdot))$时,存在$K > 0$,使得对于所有$p, q \in \mathcal{M}$,有$\left| D(p, q) - d_g(p, q)^2 \right| \leq K d_g(p, q)^4$。证明这足以使由$D$构造的图拉普拉斯算子逐点收敛,并讨论了$D$由流形参数化的一族概率测度上的Sinkhorn散度给出的例子。
英文摘要:
When analyzing a manifold learning algorithm for data lying on a smooth, compact, connected Riemannian submanifold $(\mathcal{M}, g)$ of $\mathbb{R}^d$, a key estimate for the geodesic distance $d_g$ is that there exists $K > 0$ such that $0 \leq d_g(p, q)^2 - \|p-q\|^2 \leq K d_g(p, q)^4$ for all $p, q \in \mathcal{M}$. We observe that more generally, when $\mathcal{M}$ is equipped with a smooth symmetric divergence $D$ satisfying a non-degeneracy condition and $g$ is given by $g_p := \frac{1}{2}\mathrm{Hess}_p(D(p, \cdot))$ for all $p \in \mathcal{M}$, there exists $K > 0$ such that $\left| D(p, q) - d_g(p, q)^2 \right| \leq K d_g(p, q)^4$ for all $p, q \in \mathcal{M}$. We demonstrate that this is sufficient for the pointwise convergence of graph Laplacians constructed with $D$ and discuss examples where $D$ is given by the Sinkhorn divergence on a family of probability measures parametrized by a manifold.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。