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 1902.05146cs.LGcs.ITmath.IT
收藏

基于深ReLU神经网络折叠的根格CVP

On the CVP for the root lattices via folding with deep ReLU neural networks

Telecom ParisTech(巴黎电信学院);Texas A&M University(得克萨斯农工大学);Mitsubishi Electric R&D Centre Europe(三菱电机欧洲研发中心)

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

摘要:

本文研究了点格及其神经网络译码。Rn中的格解码,称为最近向量问题(CVP),成为基本平行空间中的分类问题,具有定义边界的分段线性函数。通过对根格的研究,得到了一些理论结果。我们展示了边界函数中的片段数量如何随着折叠而显着减少,从指数到线性。这转化为一个两层ReLU网络,需要在n中呈指数增长的神经元来解决CVP,而对于深度ReLU网络,这种复杂性变成了n中的多项式。

英文摘要:

Point lattices and their decoding via neural networks are considered in this paper. Lattice decoding in Rn, known as the closest vector problem (CVP), becomes a classification problem in the fundamental parallelotope with a piecewise linear function defining the boundary. Theoretical results are obtained by studying root lattices. We show how the number of pieces in the boundary function reduces dramatically with folding, from exponential to linear. This translates into a two-layer ReLU network requiring a number of neurons growing exponentially in n to solve the CVP, whereas this complexity becomes polynomial in n for a deep ReLU network.

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。

↑