arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2307.01181math.PRcs.DScs.LGmath.STstat.MLstat.TH
收藏

用二次数量的随机点拟合椭球

Fitting an ellipsoid to a quadratic number of random points

Afonso S. Bandeira, Antoine Maillard, Shahar Mendelson, Elliot Paquette

AI总结:

研究高维标准高斯点拟合中心椭球边界的可行性阈值,借助 Bartl & Mendelson 的 Gram 矩阵集中结果,证明 n≤d^2/C 时问题以高概率可行。

摘要:

我们考虑问题 (P):当 n,d→∞ 时,将 R^d 中的 n 个标准高斯随机向量拟合到一个中心椭球的边界上。该问题被猜想存在一个尖锐的可行性转变:对任意 ε>0,若 n≤(1−ε)d^2/4,则 (P) 以高概率有解;而若 n≥(1+ε)d^2/4,则 (P) 以高概率无解。迄今为止,在否定方面仅已知平凡界 n≥d^2/2,而肯定方面的最佳结果假设 n≤d^2/polylog(d)。在本工作中,我们利用 Bartl & Mendelson (2022) 关于在尾部行为温和假设下随机向量 Gram 矩阵集中的关键结果,改进了以往方法。这使我们能够给出一个简单证明:当 n≤d^2/C(其中 C>0 为可能较大的常数)时,(P) 以高概率可行。

英文摘要:

We consider the problem $(\mathrm{P})$ of fitting $n$ standard Gaussian random vectors in $\mathbb{R}^d$ to the boundary of a centered ellipsoid, as $n, d \to \infty$. This problem is conjectured to have a sharp feasibility transition: for any $\varepsilon > 0$, if $n \leq (1 - \varepsilon) d^2 / 4$ then $(\mathrm{P})$ has a solution with high probability, while $(\mathrm{P})$ has no solutions with high probability if $n \geq (1 + \varepsilon) d^2 /4$. So far, only a trivial bound $n \geq d^2 / 2$ is known on the negative side, while the best results on the positive side assume $n \leq d^2 / \mathrm{polylog}(d)$. In this work, we improve over previous approaches using a key result of Bartl & Mendelson (2022) on the concentration of Gram matrices of random vectors under mild assumptions on their tail behavior. This allows us to give a simple proof that $(\mathrm{P})$ is feasible with high probability when $n \leq d^2 / C$, for a (possibly large) constant $C > 0$.

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。

↑