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 2204.01877math.OCcs.SYeess.SY
收藏

非欧单调算子理论及其在循环神经网络中的应用

Non-Euclidean Monotone Operator Theory with Applications to Recurrent Neural Networks

Alexander Davydov, Saber Jafarpour, Anton V. Proskurnikov, Francesco Bullo

摘要:

我们提供了一个新的转录单调算子理论的非欧有限维空间$\ell_1$和$\ell_{\infty}$。首先建立了关于非欧范数$\ell_1$或$\ell_{\infty}$单调的映射的性质。与它们的欧几里德对应物类似,关于非欧几里德范数单调的映射可以用许多算法来计算它们的零点。我们证明了计算单调算子零点的几种经典迭代法在非欧框架下是直接适用的。我们提出了一个循环神经网络的平衡计算的案例研究,并证明了铸造计算作为一个合适的运营商分裂问题,提高了收敛速度。

英文摘要:

We provide a novel transcription of monotone operator theory to the non-Euclidean finite-dimensional spaces $\ell_1$ and $\ell_{\infty}$. We first establish properties of mappings which are monotone with respect to the non-Euclidean norms $\ell_1$ or $\ell_{\infty}$. In analogy with their Euclidean counterparts, mappings which are monotone with respect to a non-Euclidean norm are amenable to numerous algorithms for computing their zeros. We demonstrate that several classic iterative methods for computing zeros of monotone operators are directly applicable in the non-Euclidean framework. We present a case-study in the equilibrium computation of recurrent neural networks and demonstrate that casting the computation as a suitable operator splitting problem improves convergence rates.

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。

↑