Skip to yearly menu bar Skip to main content


Poster

Riemannian approach to batch normalization

Minhyung Cho · Jaehyung Lee

Pacific Ballroom #130

Keywords: [ Optimization for Deep Networks ] [ Efficient Training Methods ]


Abstract:

Batch normalization (BN) has proven to be an effective algorithm for deep neural network training by normalizing the input to each neuron and reducing the internal covariate shift. The space of weight vectors in the BN layer can be naturally interpreted as a Riemannian manifold, which is invariant to linear scaling of weights. Following the intrinsic geometry of this manifold provides a new learning rule that is more efficient and easier to analyze. We also propose intuitive and effective gradient clipping and regularization methods for the proposed algorithm by utilizing the geometry of the manifold. The resulting algorithm consistently outperforms the original BN on various types of network architectures and datasets.

Live content is unavailable. Log in and register to view live content