"Dynamics and Convergence of Weight Normalization for Training Neural Networks"Montufar, GuidoWe present a result on the convergence of weight normalizedtraining of artificial neural networks. In the analysis, we consider over-parameterized 2-layer networks with rectified linear units (ReLUs) initialized at random and trained with batch gradient descent and a fixed step size. The proof builds on recent theoretical works that bound the trajectory of parameters from their initialization and monitor the network predictions via the evolution of a ''neural tangent kernel'' (Jacot et al. 2018). We discover that training with weight normalization decomposes such a kernel via the so called ''length-direction decoupling''. This in turn leads to two convergence regimes. From the modified convergence we make a few curious observations including a natural form of ''lazy training'' where the direction of each weight vector remains stationary. This is joint work with Yonatan Dukler and Quanquang Gu |
| https://www.math.ucla.edu/~montufar/ |
« back