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 2012.07032cs.ITcs.LGmath.IT
收藏

点格译码的神经网络方法

Neural network approaches to point lattice decoding

Mitsubishi Electric R&D Centre Europe(三菱电机欧洲研发中心);Telecom Paris(巴黎高等电信学院);Texas A&M University at Qatar(卡塔尔得克萨斯农工大学)

Vincent Corlay, Joseph J. Boutros, Philippe Ciblat, Loïc Brunel

摘要:

我们从神经网络的角度来描述格解码问题的复杂性。引入Voronoi-约化基的概念,将解的空间限制在一个二元集上。一方面,这个问题被证明是相当于计算一个连续的分段线性(CPWL)函数限制的基本平行。另一方面,已知由ReLU前馈神经网络计算的任何函数都是CPWL。因此,我们计算CPWL解码函数中仿射片段的数量来表征解码问题的复杂性。它在空间维度$n$上是指数的,这导致指数大小的浅神经网络。对于结构化的格子,我们表明,折叠,一种技术,相当于使用一个深神经网络,使减少这种复杂性从指数在$n$的多项式在$n$。关于非结构化MIMO格,与密集格相反,对于高斯信道上的准最佳解码,可以忽略CPWL解码函数中的许多片段。这使得解码问题变得更容易,并解释了为什么合理大小的浅神经网络在这类网格(低到中等维度)中更有效。

英文摘要:

We characterize the complexity of the lattice decoding problem from a neural network perspective. The notion of Voronoi-reduced basis is introduced to restrict the space of solutions to a binary set. On the one hand, this problem is shown to be equivalent to computing a continuous piecewise linear (CPWL) function restricted to the fundamental parallelotope. On the other hand, it is known that any function computed by a ReLU feed-forward neural network is CPWL. As a result, we count the number of affine pieces in the CPWL decoding function to characterize the complexity of the decoding problem. It is exponential in the space dimension $n$, which induces shallow neural networks of exponential size. For structured lattices we show that folding, a technique equivalent to using a deep neural network, enables to reduce this complexity from exponential in $n$ to polynomial in $n$. Regarding unstructured MIMO lattices, in contrary to dense lattices many pieces in the CPWL decoding function can be neglected for quasi-optimal decoding on the Gaussian channel. This makes the decoding problem easier and it explains why shallow neural networks of reasonable size are more efficient with this category of lattices (in low to moderate dimensions).

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。

↑