Train Feedfoward Neural Network with Layer-wise Adaptive Rate via Approximating Back-matching Propagation
arXiv:1802.09750
Abstract
Stochastic gradient descent (SGD) has achieved great success in training deep neural network, where the gradient is computed through back-propagation. However, the back-propagated values of different layers vary dramatically. This inconsistence of gradient magnitude across different layers renders optimization of deep neural network with a single learning rate problematic. We introduce the back-matching propagation which computes the backward values on the layer's parameter and the input by matching backward values on the layer's output. This leads to solving a bunch of least-squares problems, which requires high computational cost. We then reduce the back-matching propagation with approximations and propose an algorithm that turns to be the regular SGD with a layer-wise adaptive learning rate strategy. This allows an easy implementation of our algorithm in current machine learning frameworks equipped with auto-differentiation. We apply our algorithm in training modern deep neural networks and achieve favorable results over SGD.
arXiv comment12 pages, 3 figures
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- TensorFlow: A system for large-scale machine learning
- Theano: new features and speed improvements
- Large Batch Training of Convolutional Networks
- Optimizing Neural Networks with Kronecker-factored Approximate Curvature
- A Kronecker-factored approximate Fisher matrix for convolution layers
- Practical Riemannian Neural Networks
- Block-diagonal Hessian-free Optimization for Training Neural Networks
- On the Importance of Consistency in Training Deep Neural Networks
- Diagonal Rescaling For Neural Networks