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 2304.00488cs.LGmath.OC
收藏

对角线性网络中的鞍点到鞍点动力学

Saddle-to-Saddle Dynamics in Diagonal Linear Networks

EPFL(洛桑联邦理工学院)

Scott Pesme, Nicolas Flammarion

AI总结:

本文研究对角线性网络在初始化趋零极限下的梯度流,发现其呈现从鞍点到鞍点的跳跃动力学,最终达到最小 $\ell_1$-范数解,并利用类似 LARS 的递归算法刻画了鞍点与跳跃时间。

摘要:

在本文中,我们完整描述了在初始化趋于零的极限下,对角线性网络上梯度流的轨迹。我们证明了该极限流会连续地从一个训练损失的鞍点跳跃到另一个鞍点,直到达到最小 $\ell_1$-范数解。这种鞍点到鞍点动力学转化为一个增量学习过程,因为每个鞍点对应于受限于一个活动集的损失最小化器,在该活动集之外坐标必须为零。我们通过一个类似于用于计算 Lasso 路径的 LARS 算法的递归算法,显式地刻画了访问的鞍点以及跳跃时间。我们的证明利用了一种方便的弧长时间重参数化,从而能够跟踪跳跃之间的异宿转变。我们的分析对数据的假设极少,适用于参数不足和过参数化设置,并涵盖了活动坐标数量不具单调性的复杂情况。我们提供了数值实验来支持我们的发现。

英文摘要:

In this paper we fully describe the trajectory of gradient flow over diagonal linear networks in the limit of vanishing initialisation. We show that the limiting flow successively jumps from a saddle of the training loss to another until reaching the minimum $\ell_1$-norm solution. This saddle-to-saddle dynamics translates to an incremental learning process as each saddle corresponds to the minimiser of the loss constrained to an active set outside of which the coordinates must be zero. We explicitly characterise the visited saddles as well as the jumping times through a recursive algorithm reminiscent of the LARS algorithm used for computing the Lasso path. Our proof leverages a convenient arc-length time-reparametrisation which enables to keep track of the heteroclinic transitions between the jumps. Our analysis requires negligible assumptions on the data, applies to both under and overparametrised settings and covers complex cases where there is no monotonicity of the number of active coordinates. We provide numerical experiments to support our findings.

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。

↑