One Reflection Suffice

09/30/2020
by   Alexander Mathiasen, et al.
4

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset