Analysis of the Gradient Descent Algorithm for a Deep Neural Network Model with Skip-connections
arXiv:1904.05263
Abstract
The behavior of the gradient descent (GD) algorithm is analyzed for a deep neural network model with skip-connections. It is proved that in the over-parametrized regime, for a suitable initialization, with high probability GD can find a global minimum exponentially fast. Generalization error estimates along the GD path are also established. As a consequence, it is shown that when the target function is in the reproducing kernel Hilbert space (RKHS) with a kernel defined by the initialization, there exist generalizable early-stopping solutions along the GD path. In addition, it is also shown that the GD path is uniformly close to the functions given by the related random feature model. Consequently, in this "implicit regularization" setting, the deep neural network model deteriorates to a random feature model. Our results hold for neural networks of any width larger than the input dimension.
29 pages, 4 figures
References in corpus (5)
- Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks
- Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks
- Diverse Neural Network Learns True Target Functions
- A Priori Estimates of the Population Risk for Residual Networks
- Width Provably Matters in Optimization for Deep Linear Neural Networks