Analyzing Finite Neural Networks: Can We Trust Neural Tangent Kernel Theory?
arXiv:2012.04477
Abstract
Neural Tangent Kernel (NTK) theory is widely used to study the dynamics of infinitely-wide deep neural networks (DNNs) under gradient descent. But do the results for infinitely-wide networks give us hints about the behavior of real finite-width ones? In this paper, we study empirically when NTK theory is valid in practice for fully-connected ReLU and sigmoid DNNs. We find out that whether a network is in the NTK regime depends on the hyperparameters of random initialization and the network's depth. In particular, NTK theory does not explain the behavior of sufficiently deep networks initialized so that their gradients explode as they propagate through the network's layers: the kernel is random at initialization and changes significantly during training in this case, contrary to NTK theory. On the other hand, in the case of vanishing gradients, DNNs are in the the NTK regime but become untrainable rapidly with depth. We also describe a framework to study generalization properties of DNNs, in particular the variance of network's output function, by means of NTK theory and discuss its limits.
References in corpus (15)
- Playing Atari with Deep Reinforcement Learning
- Neural Tangent Kernel: Convergence and Generalization in Neural Networks
- Understanding deep learning requires rethinking generalization
- On the Number of Linear Regions of Deep Neural Networks
- Deep Neural Networks as Gaussian Processes
- On Exact Computation with an Infinitely Wide Neural Net
- Exponential expressivity in deep neural networks through transient chaos
- On Lazy Training in Differentiable Programming
- Qualitatively characterizing neural network optimization problems
- Scaling description of generalization with number of parameters in deep learning
- Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
- Tensor Programs II: Neural Tangent Kernel for Any Architecture
- Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach
- On the Selection of Initialization and Activation Function for Deep Neural Networks
- Finite Depth and Width Corrections to the Neural Tangent Kernel