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 1809.10520cs.ITmath.IT
收藏

求解二次方程无伪局部极小值的损失函数的最优构造

Towards the optimal construction of a loss function without spurious local minima for solving quadratic equations

Zhenzhen Li, Jian-Feng Cai, Ke Wei

摘要:

求服从一组二次方程$|a_k^\top x|^2=y_k$,$k=1,\cdots,m$的向量$x$的问题在许多应用中起着重要的作用。本文考虑$x$和$a_k$都是长度为$n$的实值向量的情况。针对该问题构造了一个新的损失函数,它将光滑二次损失函数与一个激活函数相结合。在高斯测量模型下,我们建立了目标解$x$是$m\gtrsim n$提供的新损失函数的唯一局部最小值(直到全局相位因子)的高概率。此外,损失函数在其鞍点周围总是具有负的方向曲率。

英文摘要:

The problem of finding a vector $x$ which obeys a set of quadratic equations $|a_k^\top x|^2=y_k$, $k=1,\cdots,m$, plays an important role in many applications. In this paper we consider the case when both $x$ and $a_k$ are real-valued vectors of length $n$. A new loss function is constructed for this problem, which combines the smooth quadratic loss function with an activation function. Under the Gaussian measurement model, we establish that with high probability the target solution $x$ is the unique local minimizer (up to a global phase factor) of the new loss function provided $m\gtrsim n$. Moreover, the loss function always has a negative directional curvature around its saddle points.

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。

↑