论文标题
一种反思就足够了
One Reflection Suffice
论文作者
论文摘要
正交重量矩阵用于许多深度学习领域。以前的许多工作试图减轻其所需的其他计算资源，以限制重量矩阵为正交。一种流行的方法利用 *许多 *住户反射。唯一的实际缺点是，许多反射会导致较低的GPU利用率。如果反射是由辅助神经网络计算得出的，我们可以通过证明 *一个 *反射就足够来减轻这一最终缺点。
Orthogonal weight matrices are used in many areas of deep learning. Much previous work attempt to alleviate the additional computational resources it requires to constrain weight matrices to be orthogonal. One popular approach utilizes *many* Householder reflections. The only practical drawback is that many reflections cause low GPU utilization. We mitigate this final drawback by proving that *one* reflection is sufficient, if the reflection is computed by an auxiliary neural network.
