cs.AI updates on arXiv.org 07月29日 12:21
Geometric structure of shallow neural networks and constructive ${\mathcal L}^2$ cost minimization
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文通过构造上界来优化未参数化浅ReLU网络中的成本最小化问题,不使用梯度下降,阐述近似和精确最小化器的几何结构,证明成本函数最小值的上界,并讨论全局最小值的特征。

arXiv:2309.10370v3 Announce Type: replace-cross Abstract: In this paper, we approach the problem of cost (loss) minimization in underparametrized shallow ReLU networks through the explicit construction of upper bounds which appeal to the structure of classification data, without use of gradient descent. A key focus is on elucidating the geometric structure of approximate and precise minimizers. We consider an $\mathcal{L}^2$ cost function, input space $\mathbb{R}^M$, output space ${\mathbb R}^Q$ with $Q\leq M$, and training input sample size that can be arbitrarily large. We prove an upper bound on the minimum of the cost function of order $O(\delta_P)$ where $\delta_P$ measures the signal-to-noise ratio of training data. In the special case $M=Q$, we explicitly determine an exact degenerate local minimum of the cost function, and show that the sharp value differs from the upper bound obtained for $Q\leq M$ by a relative error $O(\delta_P^2)$. The proof of the upper bound yields a constructively trained network; we show that it metrizes a particular $Q$-dimensional subspace in the input space ${\mathbb R}^M$. We comment on the characterization of the global minimum of the cost function in the given context.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

ReLU网络 成本最小化 非参数化
相关文章