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 1810.06397stat.MLcs.LGmath.STstat.TH
收藏

两层神经网络群体风险的先验估计

A Priori Estimates of the Population Risk for Two-layer Neural Networks

Princeton University(普林斯顿大学);Beijing Institute of Big Data Research(北京大数据研究院)

Weinan E, Chao Ma, Lei Wu

摘要:

建立了两层神经网络的人口风险的新估计。这些估计在误差率与蒙特卡罗误差率以相同方式缩放的意义上接近最优。当网络规模远大于数据集规模时,它们在过度参数化的情况下同样有效。这些新的估计是一个先验的性质,在这个意义上说,边界只取决于一些规范的基本功能,以适应,而不是在模型中的参数,与大多数现有的结果,这是一个后验的性质。使用这些先验估计,我们提供了一个角度来理解为什么双层神经网络比相关的核方法表现更好。

英文摘要:

New estimates for the population risk are established for two-layer neural networks. These estimates are nearly optimal in the sense that the error rates scale in the same way as the Monte Carlo error rates. They are equally effective in the over-parametrized regime when the network size is much larger than the size of the dataset. These new estimates are a priori in nature in the sense that the bounds depend only on some norms of the underlying functions to be fitted, not the parameters in the model, in contrast with most existing results which are a posteriori in nature. Using these a priori estimates, we provide a perspective for understanding why two-layer neural networks perform better than the related kernel methods.

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。

↑