使用生成对抗网络进行密度估计的收敛速率
Rates of convergence for density estimation with generative adversarial networks
AI总结:
本文研究原始 GAN 的非渐近性质,证明 JS 散度预言不等式,并在非参数密度估计中得到接近极小极大最优的收敛速率。
摘要:
在本工作中,我们对原始生成对抗网络(GANs)的非渐近性质进行了全面研究。我们证明了潜在密度 $\mathsf{p}^*$ 与 GAN 估计量之间 Jensen-Shannon(JS)散度的一个预言不等式,与先前已知结果相比,其统计误差项显著更优。我们的界在应用于非参数密度估计时优势明显。我们证明,GAN 估计量与 $\mathsf{p}^*$ 之间的 JS 散度以 $(\log{n}/n)^{2β/(2β+d)}$ 的速度衰减,其中 $n$ 为样本量,$β$ 决定 $\mathsf{p}^*$ 的光滑度。该收敛速率(至多相差对数因子)与所考虑密度类的极小极大最优速率一致。
英文摘要:
In this work we undertake a thorough study of the non-asymptotic properties of the vanilla generative adversarial networks (GANs). We prove an oracle inequality for the Jensen-Shannon (JS) divergence between the underlying density $\mathsf{p}^*$ and the GAN estimate with a significantly better statistical error term compared to the previously known results. The advantage of our bound becomes clear in application to nonparametric density estimation. We show that the JS-divergence between the GAN estimate and $\mathsf{p}^*$ decays as fast as $(\log{n}/n)^{2β/(2β+ d)}$, where $n$ is the sample size and $β$ determines the smoothness of $\mathsf{p}^*$. This rate of convergence coincides (up to logarithmic factors) with minimax optimal for the considered class of densities.
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。